Patents
Literature
Eureka-AI is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Eureka AI

3884 results about "Deep neural networks" patented technology

Calculation apparatus and method for accelerator chip accelerating deep neural network algorithm

The invention provides a calculation apparatus and method for an accelerator chip accelerating a deep neural network algorithm. The apparatus comprises a vector addition processor module, a vector function value calculator module and a vector multiplier-adder module, wherein the vector addition processor module performs vector addition or subtraction and/or vectorized operation of a pooling layer algorithm in the deep neural network algorithm; the vector function value calculator module performs vectorized operation of a nonlinear value in the deep neural network algorithm; the vector multiplier-adder module performs vector multiplication and addition operations; the three modules execute programmable instructions and interact to calculate a neuron value and a network output result of a neural network and a synaptic weight variation representing the effect intensity of input layer neurons to output layer neurons; and an intermediate value storage region is arranged in each of the three modules and a main memory is subjected to reading and writing operations. Therefore, the intermediate value reading and writing frequencies of the main memory can be reduced, the energy consumption of the accelerator chip can be reduced, and the problems of data missing and replacement in a data processing process can be avoided.
Owner:INST OF COMPUTING TECH CHINESE ACAD OF SCI

Named entities recognition method based on bidirectional LSTM and CRF

The invention discloses a named entities recognition method based on bidirectional LSTM and CRF. The named entities recognition method based on the bidirectional LSTM and CRF is improved and optimizedbased on the traditional named entities recognition algorithm in the prior art. The named entities recognition method based on the bidirectional LSTM and CRF comprises the following steps: (1) preprocessing a text, extracting phrase information and character information of the text; (2) coding the text character information by means of the bidirectional LSTM neural network to convert the text character information into character vectors; (3) using the glove model to code the text phrase information into word vectors; (4) combining the character vectors and the word vectors into a context information vector and putting the context information vector into the bidirectional LSTM neural network; and (5) decoding the output of the bidirectional LSTM with a linear chain condition random field to obtain a text annotation entity. The invention uses a deep neural network to extract text features and decodes the textual features with the condition random field, therefore, the text feature information can be effectively extracted and good effects can be achieved in the entity recognition tasks of different languages.
Owner:南京安链数据科技有限公司

Deep learning-based short-term traffic flow prediction method

The present invention discloses a deep learning method-based short-term traffic flow prediction method. The influence of the traffic flow rate change of the neighbor points of a prediction point, the time characteristic of the prediction point and the influence of the periodic characteristic of the prediction point on the traffic flow rate of the prediction point are considered simultaneously. According to the deep learning method-based short-term traffic flow prediction method of the invention, a convolutional neural network and a long and short-term memory (LSTM) recurrent neural network are combined to construct a Conv-LSTM deep neural network model; a two-way LSTM model is used to analyze the traffic flow historical data of the point and extract the periodic characteristic of the point; and a traffic flow trend and a periodic characteristic which are obtained through analysis are fused, so that the prediction of traffic flow can be realized. With the method of the invention adopted, the defect of the incapability of an existing method to make full use of time and space characteristics can be eliminated, the time and space characteristics of the traffic flow are fully extracted, and the periodic characteristic of the data of the traffic flow is fused with the time and space characteristics, and therefore, the accuracy of short-term traffic flow prediction results can be improved.
Owner:FUZHOU UNIV

Artificial intelligence-based object pushing method and apparatus

The invention provides an artificial intelligence-based object pushing method and apparatus. The method comprises the steps of inputting historical click behaviors of a target user to a built user model for performing learning to obtain multi-dimensional preference eigenvectors of a target user; obtaining eigenvectors of all to-be-pushed objects; inputting the eigenvectors of the to-be-pushed objects and the multi-dimensional preference eigenvectors to a trained deep neural network model for performing prediction to obtain prediction probabilities of the to-be-pushed objects; and pushing the to-be-pushed objects to the target user according to the obtained prediction probabilities. According to the method and the apparatus, the preferences of the target user are obtained through the user model built by a neural network, and the probability of possibly purchasing to-be-pushed group orders by the target user is obtained based on the deep neural network and the preferences of the target user, so that the pushing is more effective; and preference features are selected through training by the user model, so that a large amount of manpower does not need to be consumed for selection and the pushing efficiency is improved.
Owner:BEIJING BAIDU NETCOM SCI & TECH CO LTD

Voice keyword identification method and apparatus based on deep neural network

The invention provides a voice keyword identification method and apparatus based on a deep neural network. The method comprises the steps: framing the voice to be identified to obtain a plurality of voice frames; extracting features from each voice frame, and obtaining a Mel frequency cepstral coefficient MFCC sequence for each voice frame; inputting the MFCC sequence for each voice frame into a preset deep neural network model in parallel; respectively calculating the posterior probability under each neural unit of the output layer in the preset deep neural network model, for the MFCC sequence for each voice frame; forming posterior probability sequences corresponding to the plurality of voice frames through the posterior probability under each neural unit of the output layer; monitoring the posterior probability sequence under each neural unit of the output layer; and according to the comparative result between the posterior probability sequence and the probability sequence of the preset threshold, determining the keywords of the voice to be identified, and utilizing the pre-trained deep neural network to perform voice keywords identification. Therefore, the voice keyword identification method and apparatus based on a deep neural network can improve the identification speed and alleviate the problem of identification delay.
Owner:SHENZHEN WEIFU ROBOT TECH CO LTD

Modeling approach and modeling system of acoustic model used in speech recognition

ActiveCN103117060AMitigate the risk of being easily trapped in local extremaImprove modeling accuracySpeech recognitionHidden layerPropagation of uncertainty
The invention relates to a modeling approach and a modeling system of an acoustic model used in speech recognition. The modeling approach includes the steps of: S1, training an initial model, wherein a modeling unit is a tri-phone state which is clustered by a phoneme decision tree and a state transition probability is provided by the model, S2, obtaining state information of a frame level based on the fact that the initial model aligns the tri-phone state of phonetic features of training data compulsively, S3, pre-training a deep neural network to obtain initial weights of each hidden layer, S4, training the initialized network through error back propagation algorithm based on the obtained frame level state information and updating the weights. According to the modeling approach, a context relevant tri-phone state is used as the modeling unit, the model is established based on the deep neural network, weight of each hidden layer of the network is initialized through restricted Boltzmann algorithm, and the weights can be updated subsequently by means of error back propagation algorithm. Therefore, risk that the network is easy to get into local extremum in pre-training is relieved effectively, and modeling accuracy of the acoustic model is improved greatly.
Owner:INST OF ACOUSTICS CHINESE ACAD OF SCI +1
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products