Apparatus and method for training a machine learning system for denoising an input signal - Patent Application 20070123633

Abstract

A computer-implemented method for training a machine learning system (8) to denoise a provided input signal (S), training the machine learning system (8) comprising: providing a first input signal (1) and a first value (2) to a first part (4) of the machine learning system (8), the first input signal (1) characterizing a noisy signal; determining by the first part (4) a first output signal (9) for the first input signal (1) and the first value (2); and determining by a second part (5) of the machine learning system (8) a second value (6) based on the first output signal (9), the second value (6) characterizing a probability that the first output signal (9) characterizes a noisy signal. ● determining a third value (7) based on a second input signal (3) provided by the second part (5), the second input signal (3) characterizing a non-noise-containing signal, and the third value (7) characterizing a probability that the second input signal (3) characterizes a non-noise-containing signal; and ● training a machine learning system (8), the training comprising: - adapting a plurality of parameters of the first part (4) according to a gradient of the second value (6) with respect to the plurality of parameters of the first part (4); and - adapting a plurality of parameters of the second part (5) according to a gradient of the sum of the second value (6) and the third value (7) with respect to the plurality of parameters of the second part (5).

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] An advantage of the method disclosed in independent claim 1 is that a machine learning system is trained to denoise the signal, and during training the machine learning system is also fed with random values ​​as input, which allows the machine learning system to advantageously treat the problem of denoising the signal as a probabilistic problem, i.e. determining the denoised values ​​from the noisy values ​​of the signal is a probabilistic problem, and the true denoised values ​​are approximated by a probability distribution.

[0010] Disclosure of the Invention In a first aspect, the present invention provides a computer-implemented method for training a machine learning system to denoise a provided input signal, comprising: Training a machine learning system is providing a first input signal and a first value to a first portion of a machine learning system, the first input signal characterizing a noisy signal; determining, by a first portion, a first output signal for a first input signal and a first value; determining, by a second portion of the machine learning system, 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 machine learning system, the training comprising: - 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 and third values ​​for the parameters of the second part; and The present invention relates to a method comprising the steps of:

[0011] 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.

[0012] In the context of the present invention, a signal can be understood as including at least one value, but preferably a plurality of 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., a 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 a pixel of an image or a voxel of a volume entity.

[0013] The input signal can in particular be determined by a sensor, for example can be recorded.

[0014] 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.

[0015] In the context of the present invention, a machine learning system can be understood as being configured to process and denoise an input signal. The machine learning system described in the present invention 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 part and the second part of the machine learning system. The first part seeks to generate an output signal from the input signal that closely resembles the 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 the non-noised signal.

[0016] The first and second parts can therefore be understood as sub-parts of a machine learning system, each of which is also a machine learning system configured to process given input data and to determine output data.

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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.

[0024] In this context, the first part can be understood as a model for estimating an original value of the first input signal. The first part is supplied with randomly drawn first values ​​such that the first part is motivated to learn to generate different output signals when supplied with the same first input signal but with different first values. Preferably, the first part is supplied with a plurality of first values ​​for the first input signal, preferably in the form of a vector of first values, the plurality of first values ​​being extractable from a multivariate probability distribution.

[0025] 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 layers earlier than itself. 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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:

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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:

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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:

[0040] 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.

[0041] 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

[0042] 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

[0043] 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).

[0044] 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:

[0045] 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.

[0046] 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).

[0047] 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.

[0048] 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.

[0049] 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.

[0050] 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.

[0051] Embodiments of the invention will now be described in more detail with reference to the following drawings. [Brief description of the drawings]

[0052] [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

[0053] 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.

[0054] 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).

[0055] 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.

[0056] 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).

[0057] 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.

[0058] 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.

[0059] 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.

[0060] 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).

[0061] 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

[0062] 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.

[0063] In a further embodiment, it is also possible to train the machine learning system 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

[0064] 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

[0065] 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.

[0066] According to yet another embodiment, the third input signal may be processed by the second summand of the fourth equation.

[0067] 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.

[0068] 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).

[0069] The control system (40) receives a stream of sensor signals (S) of the sensor (30) at a first part (4) of the machine learning system (8). Additionally, a random generator unit (R) randomly determines one first value (2) for each sensor signal (S) and provides it to the first part (4) of the machine learning system (8). The first part (4) converts the sensor signals (S) and the first values ​​(2) into a denoised signal (x). The denoised signal (x) is then transmitted to a classifier (60).

[0070] The classifier (60) determines a classification signal (y) from the denoised signal (x). The classification signal (y) includes information for assigning one or more labels to the denoised signal (x). The classification signal (y) is sent to an optional conversion unit (80), which converts the classification 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 output signal (y) may be directly obtained as the control signal (A).

[0071] 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).

[0072] 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.

[0073] 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).

[0074] 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.

[0075] 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).

[0076] The sensors 30 may include one or more video sensors, one or more radar sensors, 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. The denoised signal x may thus be understood as an input image, and the classifier 60 may be understood as an image classifier.

[0077] The image classifier (60) can be configured to detect objects in the vicinity of the at least semi-autonomous robot based on the input image (x). The output signal (y) can include information characterizing where the object is located in the vicinity of the at least semi-autonomous robot. A control signal (A) can then be determined according to this information, for example to avoid collisions with the detected objects.

[0078] 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.

[0079] Alternatively or additionally, the control signal (A) can also be used to control the display (10a) so that, for example, objects detected by the image classifier (60) are displayed. It is also conceivable that the control signal (A) can control the display (10a) so that, if the vehicle (100) is about to collide with at least one of the detected objects, a warning signal is generated. The warning signal can be an audible warning and / or a haptic signal, for example a vibration on the steering wheel of the vehicle.

[0080] 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.

[0081] 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, classifier 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).

[0082] 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.

[0083] 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.

[0084] 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.

[0085] 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 training a machine learning system (8) to denoise a provided input signal (S), comprising: Training the machine learning system (8) comprises: providing a first input signal (1) and a first value (2) to a first part (4) of the machine learning system (8), the first input signal (1) characterizing a noisy signal and the 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 part (5) of the machine learning system (8), a second value (6) based on the first output signal (9), the second value (6) characterizing a probability that the 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 machine learning system (8), 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 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 1 further comprising:

3. 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 2 , further comprising:

4. 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 2 , further comprising:

5. 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 of claim 2.

6. 1. A computer-implemented method for determining a denoised signal (x) from an input signal (S), the method comprising: providing a first part (4) of a machine learning system (8) 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:

7. The step of providing the first portion (4) comprises a step of training the first portion (4) in the method according to claim 1. The method according to claim 6.

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 6.

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 6.

10. 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.

11. the third input signal is a sensor signal; The method of claim 2.

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

13. 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.

14. A machine-readable storage medium (46, 146) having stored thereon a computer program according to claim 13.

Images