Apparatus and method for denoising an input signal

Abstract

A computer-implemented method for determining a classification and / or regression result based on a provided input signal (S), the method comprising: providing a first portion (4), the first portion (4) configured to denoise the provided input signal (S) based on the input signal (S) and randomly selected first values ​​(2); randomly selecting a plurality of first values ​​(2); and determining a plurality of denoised signals (x) by the first portion (4), the denoised signals (x) being selected from the plurality of denoised signals (x). (x) is each determined based on a provided input signal (S) and a first value (2) from a plurality of first values ​​(2); determining a plurality of predicted values ​​based on the denoised values ​​by the model, each predicted value characterising a classification of the denoised signal or a regression result based on the denoised signal; and providing an aggregate signal (y) characterising an aggregation of the plurality of predicted values, the aggregate signal (y) characterising the classification and / or regression result determined by the method.

Description

[Technical field]

[0001] The present invention relates to a method for training a machine learning system for denoising an input signal, a method for denoising an input signal, a training device, a computer program and a machine readable storage device. [Background technology]

[0002] Prior Art “DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better” 2019, https: / / arxiv.org / abs / 1908.03826v1 by Kupyn et al. discloses a neural network for deblurring input images.

[0003] 2. Background of the Invention Denoising a signal is a problem that frequently occurs in various technical fields. In particular, if a signal is measured by a sensor, this signal may exhibit a significant amount of noise, which needs to be filtered in order to obtain a clean signal. Denoising a sensor signal is essential if the signal is to be used for a control task, for example to steer an autonomous robot.

[0004] For example, when controlling a robot on the basis of visual signals, e.g. camera images, the visual signals can be used as a means to determine a virtual copy of the environment in which the robot operates. This virtual copy of the environment can be used to determine an appropriate behavior of the robot, which can then be executed in the real world. In this context, it is essential that similar phenomena in the environment result in similar visual signals, so that the robot can respond to these visual signals consistently and reliably. If the visual signals are corrupted by a significant amount of noise, the processing of the signals can lead to erroneous actions being taken by the robot.

[0005] However, as already alluded to, the need for signal denoising is not limited to visual signals, but extends to a variety of use cases utilizing sensing devices, such as, for example, when recording acoustic signals, determining engine status with a piezoelectric sensor, or performing ranging with a radar, ultrasonic or LIDAR sensor.

[0006] In general, noise can be understood as a general term for undesired (usually unknown) changes that a signal may undergo during capture, storage, transmission, processing or transformation. There are different types of noise that can be distinguished, for example, based on their statistical characteristics (e.g., white noise, black noise or brown noise). In the context of the present invention, noise can also be understood as derived from the recording conditions of the signal, for example, raindrops seen in an image can be understood as noise, or the motion blur resulting from a motion sensor recording the signal can be understood as noise. [Prior art documents] [Non-patent literature]

[0007] [Non-Patent Document 1] Kupyn et al. ““DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better” 2019, https: / / arxiv.org / abs / 1908.03826v1” Summary of the Invention [Problem to be solved by the invention]

[0008] Known methods use deterministic models to denoise input signals. However, a problem with this approach is that noise in an image contributes to a loss of information. Using deterministic approaches, this loss of information is often not fully compensated for. It is therefore desirable to invent a method that takes into account the inherent ambiguity or uncertainty that comes with the loss of information in a signal due to noise. [Means for solving the problem]

[0009] Disclosure of the Invention In a first aspect, the present invention provides a computer implemented method for determining a classification and / or regression result based on a provided input signal, the method comprising: providing a first portion, the first portion being configured to denoise the provided input signal based on the input signal and a randomly drawn first value; randomly sampling a plurality of first values; determining, by a first portion, a plurality of denoised signals, each denoised signal from the plurality of denoised signals being determined based on the provided input signal and a first value from a plurality of first values; - determining a plurality of predicted values ​​based on the denoised values ​​by the model, each predicted value characterising a classification of the denoised signal or a regression result based on the denoised signal; providing an aggregate signal characterizing an aggregation of the plurality of predicted values, the aggregate signal characterizing a classification and / or regression result determined by the method; The present invention relates to a method comprising the steps of:

[0010] The term noise can be understood as a well-known term from the field of signal processing, i.e. as a general term for unwanted (usually unknown) changes that a signal may undergo during capture, storage, transmission, processing or transformation.

[0011] In the context of the present invention, a signal can be understood as including at least one value, but preferably several values, which can be organized in a certain form or format. For example, a signal can characterize scalar values ​​recorded over a certain time, i.e. the signal can characterize a time series. The values ​​of a signal can also be organized in the form of a vector, matrix or tensor, for example the values ​​of a signal can characterize pixels of an image or voxels of a volume entity. The supplied input signal can for example characterize an image, an acoustic signal or a recording from a sensor, such as for example a piezo sensor, a temperature sensor, a pressure sensor or a sensor for measuring acceleration.

[0012] The input signal can in particular be determined by a sensor, for example can be recorded.

[0013] When the input signal is corrupted by noise, i.e., the signal is a noisy signal, this can be understood as the loss of information in the original signal, and the noise is superimposed on some or all of the values ​​of the original signal to form the noisy signal. It is difficult, and sometimes even impossible, to recover the values ​​of the original signal. However, it is possible to estimate the values ​​of the original signal. The process of estimating the original values ​​of a signal, i.e., the values ​​of the clean signal before noise is added, can be understood as denoising. When the input signal does not contain noise, denoising should preferably determine this input signal to be a denoised signal.

[0014] The first part may be understood as a machine learning model configured and trained to denoise a signal provided to the first part, and in this sense, determining an output based on the signal by the first part may be understood as providing the signal as an input to the machine learning model to determine an output.

[0015] The first part is configured to receive as input the provided input signal and a randomly drawn first value for denoising the provided input signal. Preferably, the first value is part of a vector, matrix or tensor of random first values ​​provided as input together with the provided input signal. In other words, the first part can preferably be provided with a plurality of first values ​​for the provided input signal.

[0016] The method can be understood as determining a number of possible denoised signals for a provided input signal, and the output signal characterising the denoised signal, which is performed in a probabilistic manner, i.e. the output signal can be understood as that which a first part considers to be most likely to be a denoised version of the input signal.

[0017] Preferably, an output signal is determined for each first value. Preferably, the plurality of first values ​​are characterised by a plurality of vectors, each first value being part of a separate vector from the plurality of vectors.

[0018] Once the denoised signal is obtained, the model is used to determine a classification of the provided input signal or to perform a regression on the provided input signal, i.e. to determine a regression result on the input signal. In other words, the model is configured for classification and / or configured to perform a regression analysis. Classification can be understood as assigning at least one discrete value to the input signal, whereas performing a regression analysis can be understood as assigning at least one continuous value to the provided input signal.

[0019] Exemplary embodiments of classification may be semantic segmentation, object detection, multi-label classification, or multi-class classification.

[0020] In the method, a number of predictions are preferably determined such that one prediction is determined from the model for each denoised signal, essentially this can be understood as determining likely classification and / or regression results for a provided input signal with respect to a number of hypotheses for the denoised signals relative to the input signal.

[0021] The predicted values ​​can then be aggregated, with the term "aggregation" being understood as preferably combining the predicted values ​​into one aggregate signal, which characterizes the output of the method. For example, if all predicted values ​​are discrete values ​​characterizing a classification, known methods for combining different classifications can be used, such as majority voting. If the predicted values ​​characterize a probability or real-valued regression result, aggregation can be achieved by averaging the values. If the model outputs both predicted values ​​characterizing a classification and predicted values ​​characterizing a regression result, the predicted values ​​characterizing the classification can be aggregated and / or the predicted values ​​characterizing the regression result can be aggregated. In other words, it is preferred not to combine the predicted values ​​characterizing the classification with the predicted values ​​characterizing the regression result.

[0022] An advantage of the proposed approach is that instead of using a single denoised signal to determine the output of the method, multiple hypotheses for the denoised signal based on the input signal are determined. Thus, instead of a single denoised signal being considered when determining the output of the method, multiple different hypotheses for the denoised signal are considered. The inventors have found that this improves the accuracy of the classification determined by the method and / or the accuracy of the regression results determined by the method.

[0023] In a preferred embodiment of the method, the method additionally allows for the provision of a third value, which characterizes the variance of the plurality of predicted values.

[0024] This can also be understood as providing a measure of uncertainty regarding the output of the method together with the classification and / or regression results. Advantageously, this allows a human performing a guided human-machine interaction to infer how reliable the output of the method is, i.e. how likely it is that the classification and / or regression results are correct. Another advantage of the determined variance is that downstream applications that use the results of the method for further processing are provided with more information on which to base their decisions. For example, downstream applications can choose to reject classification and / or regression results characterized by aggregate signals if the variance value exceeds a predefined threshold.

[0025] In a preferred embodiment, the first portion may be provided based on training the first portion to denoise a provided input signal, the training of the first portion comprising: providing a first input signal and a first value to a first portion, the first input signal characterizing a noisy signal and the first value characterizing a randomly drawn value; determining, by a first portion, a first output signal for a first input signal and a first value; determining, by a second portion, a second value based on the first output signal, the second value characterizing a probability that the first output signal characterizes a noisy signal; and determining a third value based on a second input signal provided by the second portion, the second input signal characterizing a non-noise-containing signal, the third value characterizing a probability that the second input signal characterizes a non-noise-containing signal; and training the first part and the second part, the training including: - adapting the plurality of parameters of the first portion according to a gradient of a second value for the plurality of parameters of the first portion; adapting the parameters of the second part according to a gradient of the sum of the second value and the third value for the parameters of the second part; Includes steps and Includes.

[0026] Providing the first part based on training can be understood as training the first part according to the above embodiments and then using this first part for the method for determining a classification and / or regression result. Providing the first part based on training can also be understood as using the first part, which has been trained according to the above embodiments, for the method for determining a classification and / or regression result.

[0027] The first and second parts can be understood as subcomponents of a machine learning system used to train the first part. The machine learning system can be understood as a generative adversarial network (GAN). The first part can be understood as a generator of the GAN, and the second part can be understood as a discriminator of the GAN. In terms of GAN terminology, the method for training can be understood as a zero-sum game between the first and second parts of the machine learning system. The first part seeks to generate an output signal from an input signal that closely resembles a denoised signal, while the second part seeks to discriminate between the signal generated from the first part and a non-noised signal. Thus, during training, the first part learns to generate more and more "denoised-looking" input signals, until the output signal from the first part is no longer distinguishable from a non-noised signal.

[0028] Information about the characteristics of a clean signal, i.e. a signal that is free of noise or contains a negligible amount of noise, is injected into the training process via a second input signal that can be understood as a clean signal. The machine learning system is provided with information about the noisy and non-noisy signals, respectively, by the first and second input signals.

[0029] The second part can be understood as attempting to learn the difference between the output signal generated by the first part and the second input signal. In contrast, the first part seeks to generate an output signal that is indistinguishable from a clean signal. In essence, this results in the first part learning to generate a clean output signal based on a noisy input signal. In other words, the first part learns to denoise the input signal.

[0030] Preferably, the first and second parts are realized as neural networks. Preferably, the neural network is trained using a gradient-based algorithm. For training, a loss function can be defined, which is minimized during training of the machine learning system. Preferably, the second value is the negative log-likelihood of the output signal being classified as a noisy signal, and the third value is the negative log-likelihood of the second input signal being classified as a clean signal, i.e. as a signal that does not contain noise.

[0031] Then, for training, a loss function can be constructed based on the second value and the third value. For example, the loss function can be characterized by the sum of the second value and the third value. The first part can then be trained by a gradient ascent algorithm on the loss function, while the second part can be trained by a gradient descent algorithm. Alternatively, the first part can be trained by gradient descent on the negative loss function. Since the training of the first part only affects the second value, the training of the first part can also be performed by a gradient ascent algorithm based only on the second value.

[0032] It is also possible to use a second input signal in each step of each gradient-based algorithm to train multiple first input signals, in which case the loss function can characterize the average of the loss functions for the individual samples.

[0033] An advantage of the proposed approach is that the first part is supplied with a first value in addition to the first input signal, which can preferably be drawn randomly from a predefined probability distribution during each training step. In the following it will be explained why this is an advantageous feature of the invention.

[0034] As mentioned above, given the value of the noisy signal, the original value of the clean signal that became the noisy signal due to the application of noise cannot often be recovered. Without further information, the original value of the corrupted value of the signal could have been a wide range of values. However, a probability distribution of the original values ​​can be determined. If such a probability distribution exists, it allows several ways to estimate the original value, for example by randomly drawing a value from this distribution and providing this value as an estimate of the original value, or by drawing several values ​​from the probability distribution and providing the expectation of these extracted values ​​as an estimate of the original value.

[0035] The first part can thus be understood as a model for estimating an original value of the first input signal. The first part is fed with randomly drawn first values ​​such that the first part is motivated to learn to generate different output signals when fed the same first input signal but with different first values. Preferably, the first part is fed with a plurality of first values ​​for the first input signal, the plurality of first values ​​being extractable from a multivariate probability distribution.

[0036] Another advantage of the proposed invention is that the first part is able to learn to denoise input signals of different types of noise. For example, if the input signal to be denoised is an image, the type of noise can be random pixel noise, glare, blur, or noise that depends on the image content, e.g. rain. The inventors have discovered that the first part is able to learn to remove multiple different types of noise. The first value has the effect of guiding the process of denoising. For example, if a neural network is used as the first part, noise can be provided as input to the neural network in any layer of the neural network, and the position of the layer where the first value is provided as input has a direct effect on the denoising. For example, if the first value is provided as input to the first layer of the neural network, the first value will affect local parts of the input signal, e.g. adjacent pixels in an image, or adjacent points in an audio signal, because the neural network processes local features in its earlier layers. In contrast, providing the first value as input to the last layer of the neural network affects the entire part of the input signal, e.g., a region of an image or a segmentation of an audio signal, because the neural network processes global features in its later layers. If the first value is provided to a layer between the first and last layer, the influence can be gradually shifted from the local part of the input signal (earlier layers) to the global part of the input signal (later layers). This is particularly useful if the type of noise removed by the first part can be narrowed. For example, if it is known that the noise expected in the input signal is of a local nature, e.g., pixel noise, the first value can be provided to an earlier layer. In contrast, if the noise expected in the input signal is of a global nature, e.g., noise due to weather effects such as rain, the first value can be provided to a later layer.

[0037] In summary, the first value has the effect of steering the denoising process and improves the quality of the denoised signal, i.e. makes it possible to achieve better denoising performance.

[0038] The type of noise that the first portion should learn to remove can be defined by one or more first input signals. If a certain type of noise is present in the first input signal, the first portion can learn to remove that type of noise. Thus, the first input signal can be understood as a training data set, and the particular configuration of noise in the first input signal can be understood as defining what types of noise can be removed from the input signal using the first portion after training.

[0039] Another advantage of training a single model to handle multiple types of noise is that the first part also learns to generalize better to new noises at inference time than if it was trained on only one type of corruption. In other words, if a noise not observed during the training of the first part is presented to the first part after training, the first part will be able to more accurately predict the denoised output signal.

[0040] In summary, the specific design of the machine learning system combined with the proposed training algorithm results in a first part that can estimate the clean version of the input signal provided to different types of noise.Because the first part is able to distinguish between different types of noise, the generated output signal will more accurately resemble the clean signal.In other words, the denoising of the input signal is improved.

[0041] A method for training a machine learning system includes providing a third input signal and a fourth value to the first portion, the third input signal not characterizing the noisy signal; and determining, by the first portion, a second output signal for a third input signal and a fourth value; - adapting a plurality of parameters of the first part according to a deviation of the second output signal relative to a third input signal; It is also possible to further include:

[0042] The main advantage of this particular embodiment is that the first part learns not to denoise input signals that do not contain noise in the first place. In general, this improves the performance of the first part in dealing with both input signals that contain noise and input signals that do not exhibit noise. For example, the machine learning system can be configured to process camera images recorded over the course of a day. At dawn, dusk and night, images may contain noise due to the camera recording process, while images recorded during the day when sufficient light is available may only exhibit a negligible amount of noise. Now, the first part trained with such additional features could be applied to camera images regardless of the actual amount of noise present in the image.

[0043] Another advantage of this embodiment is that the first part is trained to take the input signal into account when determining the output signal. In other words, this allows the first part to not rely solely on the first value when determining the output signal. This improves noise rejection even further.

[0044] The fourth value, like the first value, can preferably be randomly drawn. In a preferred embodiment, a plurality of fourth values ​​can be provided for the third input signal, for example in the form of a vector, matrix or tensor.

[0045] In further embodiments, the second input signal can be used as the third input signal, in these embodiments, the first value can be used as the fourth value, or another random value can be drawn as the fourth value.

[0046] The deviation of the second output signal relative to the third input signal can be characterized by a loss function that determines the distance between the second output signal and the third output signal, for example, the Euclidean distance or the Manhattan distance. This loss function can be considered as forcing the first part to learn to copy the input signal as the output signal in the absence of noise in the input signal. Thus, the loss function described above can be considered as an identity loss function. For training, the identity loss function can be added to the loss function from the GAN training above to form a global loss function. Preferably, the identity loss function can be weighted by a predetermined coefficient in the global loss function.

[0047] In a preferred embodiment, the method for training comprises: determining, by the first portion, a fifth value characterizing a classification of a type of noise characterized by the first input signal based on the first input signal and the first value; - adapting a plurality of parameters of the first part according to a deviation between a class characterized by the fifth value and a class of a noise type corresponding to the first input signal; It is also possible to further include:

[0048] This approach can be understood as additionally tasking a first part of a machine learning system with the task of classifying the type of noise present in the input signal. The inventors have discovered that this form of supervised training of the first part acts as a regularization of the training, improving the performance of the first part even further since it is presented with even more information about the noise to be removed.

[0049] In this embodiment, the first input signal is assigned a class label that characterizes the type of noise exhibited by the first input signal. The class label can be assigned by an expert or can be determined via unsupervised labeling methods, for example by clustering the noisy first input signal, where the cluster membership of the first input signal determines the desired class that the first portion should predict. In either case, the assigned class and / or the assigned class label can be considered as corresponding to the first input signal.

[0050] Another advantage of this particular embodiment is that a downstream application can be provided with the output signal for a given input signal and the classification of the first part of the machine learning system. In this way, the downstream application is provided with more information about the input signal before noise removal, which allows the downstream application to process the output signal even more accurately.

[0051] In a preferred embodiment, the method for training comprises: determining, by the first portion, a fifth value characterizing a classification of a noise type characterized by the third input signal based on the third input signal and the fourth value; - adapting a plurality of parameters of the first part according to the deviation between a class characterized by a fifth value and a class characterizing the absence of noise; It is also possible to further include:

[0052] An advantage of this embodiment is that the first part also learns to classify the input signal without noise, which the inventors have found improves the denoising performance of the first part even further.

[0053] When training with a third input signal, the deviation of the second output signal from the third input signal is expressed by the formula

number

number

number

number

number

[0054] A plurality of third input signals may be used for training, for example in the form of batch-by-batch training of a machine learning system. Each first value for each third input signal in the batch of third input signals used for training may be randomly drawn for each training step. In this case, the loss function is preferably the expected value in the above formula:

number

[0055] The advantage of this embodiment is that the first part is trained to learn to output an input signal as an output signal when the input signal is noise-free. This is achieved by training the first part not to consider the first value when encountering a noise-free input signal. This independent behavior for the first value in the case of a non-noise-containing signal is achieved by providing the first part with two randomly drawn first values ​​for a third input signal, and training the first part of the machine learning system to minimize the distance between the output signal for the third input signal y and the two randomly drawn first values ​​(see the second summand of the loss function).

[0056] In yet another embodiment, the formula

number

number

number

number

number

[0057] For training, signals

number

number

[0058] Training the first part in this way gives us the margin of the optimization problem, i.e.

number

number

[0053] It entails a hyper-parameter τ, which can be understood as characterizing the difference in variance of the output signal relative to

[0059]

number

[0060] The first part should not make any changes to the clean signal, i.e. the input signal that does not contain noise, so the term

number

number

number

number

number

[0061] In another aspect, the invention provides a computer-implemented method for determining a denoised signal from an input signal, the method comprising: - providing a first part according to an embodiment of the training method presented above; determining, by a first portion, an output signal based on the input signal and a randomly drawn first value; providing the output signal as a denoised signal; The present invention relates to a method comprising the steps of:

[0062] The method for denoising can be understood as applying a first part of a machine learning system obtained in the method for training. The feature of the step of providing the first part can be understood as training the first part according to an embodiment of the training method presented above and then providing the trained first part. Alternatively, this feature can be understood as using a first part configured according to an embodiment of the invention and / or a first part trained using a method according to an embodiment of the invention.

[0063] It is possible to use the first part of the machine learning system for denoising, since it has learned to determine the denoised signal given the input signal. The advantage is that the first part can determine the denoised signal with high accuracy. Another advantage of the proposed approach is that the noise-free input signal can also be used as input for the denoising method, since the first part has learned to treat the noise-free input signal separately, i.e. to preserve the value of the noise-free input signal as best as possible. Thus, in a signal processing pipeline, the first part can be applied to the input signal before further processing, since the first part generally improves the performance of downstream tasks, such as classification of data from the input signal (e.g. object detection in an image, speaker classification in an audio signal, classification of when an engine injector valve is closed, where the sensor signal characterises data from a piezo sensor of the valve).

[0064] The advantage of this approach is that the output signal (which can be understood as a denoised input signal) can be used more efficiently for downstream tasks, since denoising allows for better processing in the downstream task, for example when classifying the output signal as a proxy for classifying the input signal, thereby improving the performance of the downstream task, for example classification.

[0065] For example, the denoised signal can be used as an input to a virtual sensor to determine characteristics of the input signal that are not measured by the input signal itself.

[0066] Typically, the noise-reduced signal is available as an input to a control system, the control system being configured to determine control signals for actuators based on the noise-reduced signal.

[0067] The control system can be configured, for example, to control an at least semi-autonomous robot, where the input signals are sensor signals characterizing the robot's perception of its environment and the control signals control at least a part of the robot's behavior. An advantage here is that by denoising the input signals, the control system can more accurately perceive the environment and thus determine better behaviors by the robot through more appropriate control signals for actuators.

[0068] Embodiments of the invention will now be described in more detail with reference to the following drawings. [Brief description of the drawings]

[0069] [Figure 1] FIG. 1 illustrates a machine learning system. [Diagram 2] FIG. 1 illustrates a training system for training a machine learning system. [Diagram 3] FIG. 1 illustrates a control system for controlling an actuator based on an output signal of a machine learning system. [Figure 4] FIG. 1 illustrates a control system for controlling an at least semi-autonomous vehicle. [Diagram 5] FIG. 2 shows a control system for controlling the valves. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0070] Description of the embodiments FIG. 1 shows an embodiment of a machine learning system (8). The machine learning system comprises a first part (4) called a generator and a second part (5) called a discriminator. The machine learning system can be understood as a generative adversarial network. In this embodiment, the generator (4) and the discriminator (5) can preferably be provided by respective neural networks. The machine learning system (8) can therefore also be understood as a larger neural network, where the generator (4) and the discriminator (5) form sub-neural networks of the machine learning system (8). In further embodiments, the generator (4) and / or the discriminator (5) can also be provided by other machine learning models, for example a support vector machine.

[0071] The figure shows how the machine learning system can be configured for training. The machine learning system is provided with a first input signal (1), which is forwarded to a generator (4). The first input signal (1) characterizes a noisy signal, which the machine learning system (8) should learn to denoise. The machine learning system (8) is also provided with a randomly drawn first value (2), which is also forwarded to the generator (4). In this embodiment, the first value (2) is drawn from a standard normal distribution. In further embodiments, other probability distributions can also be used to draw the first value (2). In yet other embodiments, the machine learning system can also be provided with a vector (2) of first values, which is drawn from a multivariate probability distribution, preferably from a multivariate standard normal distribution. The machine learning system (8) is also provided with a second input signal (3), which characterizes a non-noisy signal, i.e. a clean signal. The second input signal (3) is forwarded to a discriminator (5).

[0072] The first input signal (1) and the second input signal (3) may in particular be sensor signals received from a sensing device such as an optical device (e.g. a camera, a radar sensor, a LIDAR sensor, an ultrasonic sensor, a thermal sensor), a piezoelectric sensor, a microphone or a sensor for measuring current or voltage.

[0073] The generator (4) receives a first input signal (1) and a first value (2) and determines an output signal (9) based on the first input signal (1) and the first value (2). The output signal (9) can be understood as characterizing a signal of the same type as the first signal (1). For example, if the first input signal (1) is an image, the output signal (9) can be understood as a denoised image obtained based on the first input signal (1).

[0074] The output signal (9) is received by the discriminator (5) together with the second input signal (2). The discriminator (5) is configured to classify both the output signal (9) and the second input signal (3). To this end, the discriminator (5) can assign a second value (6) to the output signal (9), the second value (6) characterizing the probability that the output signal (9) is a noisy signal. The discriminator (5) can also assign a third value (7) to the second input signal (3), the third value (7) characterizing the probability that the second input signal (3) is a clean signal. For example, the second value (6) and the third value (7) can characterize a probability, a log-likelihood or preferably a negative log-likelihood, respectively.

[0075] FIG. 2 illustrates an embodiment of a training system (140) for training a machine learning system (8). Training is performed based on a training data set (T). The training data set (T) may include a plurality of first input signals (1) characterizing noisy signals and a plurality of second input signals (3) characterizing clean signals. Alternatively, the training data set (T) may not include a plurality of first input signals (1). In that case, a plurality of first input signals (1) can be determined for training based on the plurality of second input signals (3), for example by selecting a signal from the plurality of second input signals (3) and adding noise to the selected signal.

[0076] For training, the training data unit (150) accesses a computer-implemented database (St2), which provides a training data set (T). The training data unit (150) preferably randomly determines at least one first input signal (1) and at least one second output signal (2) from the training data set (T) and provides the at least one first input signal (1) and the at least one second output signal (2) to the machine learning system (8). Additionally, the training data unit (150) randomly determines a first value (2), preferably a vector (2) of first values, and provides it to the machine learning system (8). If the training data set (T) does not include the first input signal (1), the training data unit (150) can also randomly select a signal from a plurality of second input signals (3), add noise to the selected signal, and provide the resulting noise-containing signal to the machine learning system (8) as the first input signal (1). In another preferred embodiment, the training data unit (150) may also randomly select batches of the first input signal (1) and the second input signal (3), in which case both the batch size and the ratio between the first input signal (1) and the second input signal (2) are hyperparameters of the training procedure.

[0077] In either case, at least one first input signal (1) and at least one second input signal (3) are transferred to a machine learning system (8), which determines a second value (6) for each first input signal (1) and a third value (7) for each second input signal (3).

[0078] The second value (6) and the third value (7) are then forwarded to a modification unit (180). The modification unit (180) then determines new parameters (Φ') for the machine learning system (8) based on the second value (6) and the third value (7). The new parameters (Φ') include new parameters for the first part (4) and the second part (5) of the machine learning system (8). Preferably, determining the new parameters (Φ') is achieved by gradient descent, the gradient being determined based on a loss function. To determine the new parameters for the second part (5), the loss function is preferably of the first formula:

number

number

number

number

number

[0079] Additionally, the training system (140) may include at least one processor (145) and at least one machine-readable storage medium (146) containing instructions that, when executed by the processor (145), cause the training system (140) to perform a training method according to one of the aspects of the present invention.

[0080] In a further embodiment, the machine learning system may be trained to not denoise input signals that no longer contain noise. To this end, new parameters of the first part are added to the third equation:

number

number

number

number

number

[0081] According to yet another embodiment, the first part (4) can also be configured to determine a classification of the type of noise provided to the first input signal (1), e.g. additive noise, quantization error, multiplicative noise or shot noise. The machine learning system can be configured in particular to determine that if the input signal does not contain noise, it is a class that characterizes the label "no noise". The machine learning system can also be provided with a label of the first input signal (1), which label characterizes the class of noise to which the noise from the first input signal (1) belongs. The new parameters for the first part (4) are then calculated, preferably according to a fourth equation:

number

number

number

[0082] The labels can also be obtained by clustering the unlabeled first input signals (1) and assigning the same label to the first input signals (1) in one cluster.

[0083] According to yet another embodiment, the third input signal may be processed by the second summand of the fourth equation.

[0084] 3 shows an embodiment of a control system 40 for controlling the actuator 10 in its environment. The actuator 10 and its environment 20 are collectively referred to as the actuator system. A sensor 30 senses the state of the actuator system, preferably at equally spaced time points. The sensor 30 may include multiple sensors. Preferably, the sensor 30 is an optical sensor that takes images of the environment 20. An output signal S of the sensor 30 (or an output signal S for each of the sensors, if the sensor 30 includes multiple sensors) encoding the sensed condition is transmitted to the control system 40.

[0085] Thereby, the control system (40) receives the stream of sensor signals (S) and then calculates a set of control signals (A) depending on the stream of sensor signals (S), which are then transmitted to the actuators (10).

[0086] The control system (40) receives a stream of sensor signals (S) of the sensor (30) in a first part (4) of the machine learning system (8). Additionally, a random generator unit (R) randomly determines a number of first values ​​(2) for each sensor signal (S). The first part (4) determines one output signal (x) for each first value (2) and for that sensor signal (S). The output signal (x) can be understood as a denoised signal (x). Thus, there are a number of output signals (x) for each sensor signal (S). Then, for one sensor signal (S), each output signal (x) is processed by a second machine learning system (60), preferably by a classifier or by a machine learning model configured to perform a regression analysis. For each of the output signals (x) determined for a sensor signal (S), the second machine learning system determines an output, and then the different outputs for the output signals (x) are aggregated into an aggregate signal (y). For example, if the second machine learning system (60) is configured to perform classification, the outputs determined from the second machine learning system (60) may be aggregated by majority voting to determine an aggregate signal (y). If the second machine learning system (60) is configured to perform regression analysis, the different outputs for the output signals (x) may be summed or averaged to determine an aggregate signal (y).

[0087] In a further embodiment, the aggregate signal (y) may further include a value characterizing the variance of the multiple distinct outputs determined from the second machine learning system (60), e.g., the standard deviation of the multiple distinct outputs.

[0088] The aggregate signal (y) is sent to an optional conversion unit (80), which converts the aggregate signal (y) into a control signal (A). The control signal (A) is then sent to the actuator (10) for controlling the actuator (10) accordingly. Alternatively, the aggregate signal (y) may be obtained directly as the control signal (A).

[0089] Actuator (10) receives control signal (A) and is controlled accordingly to perform an action corresponding to control signal (A). Actuator (10) may include control logic that converts control signal (A) into a further control signal, which is then used to control actuator (10).

[0090] In further embodiments, the control system 40 may include the sensor 30. In yet other embodiments, the control system 40 may alternatively or additionally include the actuator 10.

[0091] In yet another embodiment, it is envisaged that the control system (40) controls the display (10a) instead of or in addition to the actuator (10).

[0092] Additionally, the control system (40) may include at least one processor (45) and at least one machine-readable storage medium (46) having instructions stored thereon that, when executed, cause the control system (40) to perform a method according to one aspect of the present invention.

[0093] FIG. 4 illustrates an embodiment in which the control system (40) is used to control an at least semi-autonomous robot, such as an at least semi-autonomous vehicle (100).

[0094] The sensors (30) may include one or more video sensors, and / or one or more radar sensors, and / or one or more ultrasonic sensors, and / or one or more LiDAR sensors, some or all of which are preferably, but not necessarily, on board the vehicle (100). Thus, the denoised signal (x) can be understood as an image, and the second machine learning system (60) can be understood as an image classifier or an image regressor (i.e., a model configured for image regression).

[0095] The second machine learning system (60) can be configured to detect an object in the vicinity of the at least semi-autonomous robot based on the provided output signal (x). The aggregate signal (y) can include information characterizing where the object is located in the vicinity of the at least semi-autonomous robot. Additionally, the aggregate signal (y) can include information regarding the variance of the object's position and / or extension, for example in the form of an uncertainty value. A control signal (A) can then be determined according to any one or all of these pieces of information, for example to avoid collisions with the detected object.

[0096] The variance information contained in the aggregate signal (y) can be used, for example in a Kalman filter, to track objects detected in the denoised signal (x), in which case the variance information can be used as the variance of the observation noise.

[0097] The actuators (10), preferably on board the vehicle (100), may be provided by the brakes, propulsion system, engine, drive train or steering of the vehicle (100). A control signal (A) may be determined such that the actuators (10) are controlled such that the vehicle (100) avoids a collision with the detected objects. The detected objects may also be classified according to their identity, e.g. pedestrian or tree, which the image classifier (60) considers to be most likely, and the control signal (A) may be determined depending on the classification.

[0098] Alternatively or additionally, the control signal (A) can also be used to control the display (10a) such that objects detected by the second machine learning system (60) are displayed. It is also possible that the control signal (A) can control the display (10a) such that a warning signal is generated if the vehicle (100) is about to collide with at least one of the detected objects. The warning signal can be an audible warning and / or a haptic signal, for example a vibration on the steering wheel of the vehicle.

[0099] In further embodiments, the at least semi-autonomous robot can be provided by another mobile robot (not shown), which can move, for example, by flying, swimming, diving or walking. The mobile robot may in particular be an at least semi-autonomous lawnmower or an at least semi-autonomous cleaning robot. In all the above embodiments, the control signal (A) can be determined such that the propulsion unit and / or steering and / or braking of the mobile robot are controlled so that the mobile robot can avoid a collision with said identified object.

[0100] 4 illustrates one embodiment for controlling valve 10. In this embodiment, sensor 30 is a pressure sensor that senses the pressure of a fluid that may be output by valve 10. In particular, second machine learning system 60 can be configured to accurately determine the amount of fluid jet that will be dispensed by valve 10 based on a time series of pressure values ​​(x).

[0101] In particular, the valve 10 may be part of a fuel injector for an internal combustion engine, the valve 10 being configured to inject fuel into the internal combustion engine, and the valve 10 may then be controlled in future injection processes based on the determined injection quantity such that any over- or under-injection of fuel is compensated accordingly.

[0102] Alternatively, the valve 10 may be part of an agricultural fertilizer system, in which case the valve 10 is configured to apply fertilizer, and the valve 10 may then be controlled in future application operations based on the determined fertilizer application rate such that excessive or insufficient fertilizer application rates are compensated accordingly.

[0103] The term "computer" may be understood to encompass any device for processing certain computational rules, which may be in the form of software, hardware, or a mixture of software and hardware.

[0104] In general, plurals may be understood to be subscripted, i.e., each element of a plural is assigned a unique subscript, preferably by assigning consecutive integers to the elements contained in the plural. Preferably, if a plural contains N elements, and N is the number of elements in the plural, then these elements are assigned integers from 1 to N. It may also be understood that each element contained in a plural may be accessed via the subscript of the element.

Claims

1. 1. A computer-implemented method for determining a classification and / or regression result based on a provided input signal (S), the method comprising: providing a first portion (4), the first portion (4) being configured to denoise the provided input signal (S) based on the input signal (S) and a randomly drawn first value (2); randomly sampling a plurality of first values ​​(2); determining a plurality of denoised signals (x) by said first portion (4), each denoised signal (x) from said plurality of denoised signals (x) being determined based on said provided input signal (S) and a first value (2) from said plurality of first values ​​(2); - determining a plurality of predicted values ​​based on the denoised values ​​by the model, each predicted value characterising a classification of the denoised signal or a regression result based on the denoised signal; - providing an aggregate signal (y) characterizing an aggregation of the plurality of predicted values, said aggregate signal (y) characterizing a classification and / or regression result determined by the method; Including, The first part (4) is provided on the basis of training the first part (4) to denoise the provided input signal (S), Training the first part (4) comprises: - providing said first portion (4) with a first input signal (1) and a first value (2), said first input signal (1) characterizing a noisy signal and said first value (2) characterizing a randomly drawn value; determining, by said first part (4), a first output signal (9) for said first input signal (1) and said first value (2); determining, by a second portion (5), a second value (6) based on said first output signal (9), said second value (6) characterizing a probability that said first output signal (9) characterizes a noisy signal; determining a third value (7) based on a second input signal (3) provided by said second part (5), said second input signal (3) characterizing a non-noise-containing signal, said third value (7) characterizing a probability that said second input signal (3) characterizes a non-noise-containing signal; training said first portion (4) and said second portion (5), said training comprising: adapting a plurality of parameters of the first portion (4) according to a gradient of the second value (6) with respect to the plurality of parameters of the first portion (4); adapting the parameters of the second portion (5) according to the gradient of the sum of the second value (6) and the third value (7) for the parameters of the second portion (5); and A method comprising:

2. The method additionally provides a third value; the third value characterizing a variance of the plurality of predicted values. The method of claim 1.

3. The method comprises: - providing a third input signal and a fourth value to the first portion (4), the third input signal characterizing a non-noise-containing signal; determining, by said first part (4), a second output signal for said third input signal and said fourth value; - adapting a plurality of parameters of said first part (4) according to a deviation of said second output signal with respect to said third input signal; The method of claim 2 , further comprising:

4. The method comprises: determining, by said first portion (4), a fifth value characterizing a classification of the type of noise characterized by said first input signal (1) based on said first input signal (1) and said first value (2); - adapting a plurality of parameters of said first part (4) according to the deviation between a class characterized by said fifth value and a class of a noise type corresponding to said first input signal (1); The method of claim 3 further comprising:

5. The method comprises: determining, by said first portion (4), a fifth value characterizing a classification of a type of noise characterized by said third input signal based on said third input signal and said fourth value; - adapting a plurality of parameters of said first part according to the deviation between a class characterized by said fifth value and a class characterizing the absence of noise; The method of claim 3 further comprising:

6. The deviation of the second output signal with respect to the third input signal is expressed by the formula [0010] where: [0025] is the third input signal, and G is the first portion. The method according to claim 3.

7. 1. A computer-implemented method for determining a denoised signal (x) from an input signal (S), the method comprising: - providing a first part (4) trained according to the method of claim 1; determining, by said first part (4), an output signal (x) based on said input signal (S) and on a randomly drawn first value (2); providing the output signal (x) as a denoised signal (x); A method comprising:

8. The denoised signal (x) is used as an input to a control system (40); The control system (40) is configured to determine a control signal (A) for an actuator (10) based on the noise-removed signal (x). The method according to claim 7.

9. The denoised signal (x) is used as an input to a virtual sensor (30) for determining a characteristic of the input signal (S) that is not measured by the input signal (S) itself. The method according to claim 7.

10. The input signal (S) is a sensor signal. The method of claim 1.

11. the first input signal and / or the second input signal and / or the input signal (S) is a sensor signal; The method of claim 1.

12. the third input signal is a sensor signal; The method according to claim 3.

13. A training system (140) configured to perform the method of claim 1.

14. A computer program configured, when executed by a processor (45, 145), to cause said processor (45, 145) to carry out all the steps of the method according to claim 1.

15. A machine-readable storage medium (46, 146) having stored thereon a computer program according to claim 14.

Images