In some examples, a method includes receiving an artificial intelligence (AI) system scenario definition file from a user, parsing the definition file and building an application workflow graph for the AI system, and mapping the application workflow graph to an execution pipeline. In some examples, the method further includes automatically generating, from the workflow graph, application executable binary code implementing the AI system, and outputting the application executable binary code to the user. In some examples, the execution pipeline includes one or more building blocks, and the method then further includes collecting running performance of each of the building blocks of the execution pipeline in a runtime environment.

In some examples, a method includes receiving an artificial intelligence (AI) system scenario definition file from a user, parsing the definition file and building an application workflow graph for the AI system, and mapping the application workflow graph to an execution pipeline. In some examples, the method further includes automatically generating, from the workflow graph, application executable binary code implementing the AI system, and outputting the application executable binary code to the user. In some examples, the execution pipeline includes one or more building blocks, and the method then further includes collecting running performance of each of the building blocks of the execution pipeline in a runtime environment.

A neural network system is configured to receive an input image and to generate a classification output for the input image. The neural network system includes: a separable convolution subnetwork comprising a plurality of separable convolutional neural network layers arranged in a stack one after the other, in which each separable convolutional neural network layer is configured to: separately apply both a depthwise convolution and a pointwise convolution during processing of an input to the separable convolutional neural network layer to generate a layer output.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving, by a neural network (NN), a dataset for generating features from the dataset. A first set of features is computed from the dataset using at least a feature layer of the NN. The first set of features i) is characterized by a measure of informativeness; and ii) is computed such that a size of the first set of features is compressible into a second set of features that is smaller in size than the first set of features and that has a same measure of informativeness as the measure of informativeness of the first set of features. The second set of features if generated from the first set of features using a compression method that compresses the first set of features to generate the second set of features.

Described herein is a machine learning mechanism implemented by one or more computers, the mechanism having access to a base neural network and being configured to determine a simplified neural network by iteratively performing the following set of steps: forming sample data by sampling the architecture of a current candidate neural network; selecting, in dependence on the sample data, an architecture for a second candidate neural network; forming a trained candidate neural network by training the second candidate neural network, wherein the training of the second candidate neural network comprises applying feedback to the second candidate neural network in dependence on a comparison of the behaviours of the second candidate neural network and the base neural network; and adopting the trained candidate neural network as the current candidate neural network for a subsequent iteration of the set of steps.

Described herein is a machine learning mechanism implemented by one or more computers, the mechanism having access to a base neural network and being configured to determine a simplified neural network by iteratively performing the following set of steps: forming sample data by sampling the architecture of a current candidate neural network; selecting, in dependence on the sample data, an architecture for a second candidate neural network; forming a trained candidate neural network by training the second candidate neural network, wherein the training of the second candidate neural network comprises applying feedback to the second candidate neural network in dependence on a comparison of the behaviours of the second candidate neural network and the base neural network; and adopting the trained candidate neural network as the current candidate neural network for a subsequent iteration of the set of steps.

A graph neural network to predict net parasitics and device parameters by transforming circuit schematics into heterogeneous graphs and performing predictions on the graphs. The system may achieve an improved prediction rate and reduce simulation errors.

Disclosed herein is a search method performed by a server, including: receiving a user question from a user terminal; generating a user question vector for the user question; selecting similar question candidates based on a similarity to the user question vector; generating an answer to the user question based on the similar question candidates; and transmitting the answer to the user question to the user terminal.

Training an artificial neural network, ANN, which translates one or more input variables into one or more output variables, using learning data sets including learning input variable values having measurement data, and associated learning output variable values, by: mapping learning input variable values from a learning data set onto output variable values using the ANN; processing deviations of the output variable values from the respective learning output variable values using a cost function to form a measure of the error of the ANN when processing the learning input variable values; determining from the error, by backpropagation, changes in parameters, the execution of which, when learning input variable values are further processed by the ANN, improve the evaluation of the obtained output variable values by the cost function, and applying said changes to the ANN; wherein a subset of the output variable values is excluded from consideration in the backpropagation.

A method and device for model compression of a neural network. The method comprises: recording input and output parameters of each layer of network in a network structure; dividing the network structure into several small networks according to the input and output parameters; setting a pruning flag bit of a first convolutional layer in each small network to be zero to obtain a pruned small network; training each pruned small network to obtain a network weight and a weight mask; recording a pruned channel index number of each convolutional layer of a pruned small network with the weight mask of zero; and carrying out decomposition calculation on each pruned small network according to the pruned channel index number. According to the method, a calculation amount and the size of a model is reduced, and during network deployment, the model can be loaded with one click, thus reducing usage difficulty.