Snap Inc.

Moffett Technologies Co., Limited

Moffett International Co., Limited

Enxu Yan

Ning Xu

Yuncheng Li

Zhou Ren

Zhibin Xiao

Wei Wang

Tan Yu

Yong Lu

Jiachao Liu

Sergey Tulyakov

Aleksei Stoliar

Dongkuan Xu

Aleksei Podkin

Embodiments disclosed herein allowed neural networks to be pruned. The inputs and outputs generated by a reference neural network are used to prune the reference neural network. The pruned neural network may have a subset of the weights that are in the reference neural network.

Neural network pruning method and system via layerwise analysis

A neural network pruning system can sparsely prune neural network models using an optimizer based approach that is agnostic to the model architecture being pruned. The neural network pruning system can prune by operating on the parameter vector of the full model and the gradient vector of the loss function with respect to the model parameters. The neural network pruning system can iteratively update parameters based on the gradients, while zeroing out as many parameters as possible based a preconfigured penalty.

Optimizer based prunner for neural networks

Embodiments disclose bank-balanced-sparse activation neural network models and methods to generate the bank-balanced-sparse activation neural network models. According to one embodiment, a neural network sparsification engine determines a first deep neural network (DNN) model having two or more hidden layers. The engine determines a bank size, a bank layout, and a target sparsity. The engine segments the activation feature maps into a plurality of banks based on the bank size and the bank layout. The engine generates a second DNN model by increasing a sparsity for each bank of activation feature map based on the target sparsity, wherein the second DNN model is used for inferencing.

Bank-balanced-sparse activation feature maps for neural network models

Systems and methods are disclosed for capturing multiple sequences of views of a three-dimensional object using a plurality of virtual cameras. The systems and methods generate aligned sequences from the multiple sequences based on an arrangement of the plurality of virtual cameras in relation to the three-dimensional object. Using a convolutional network, the systems and methods classify the three-dimensional object based on the aligned sequences and identify the three-dimensional object using the classification.

Sequence-of-sequences model for 3D object recognition

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for balanced-weight sparse convolution processing. An exemplary method comprises: obtaining an input tensor and a plurality of filters at a layer within a neural network; segmenting the input tensor into a plurality of sub-tensors; dividing a channel dimension of each of the plurality of filters into a plurality of channel groups; pruning each of the plurality of filters so that each of the plurality of channel groups of each filter comprises a same number of non-zero weights; segmenting each of the plurality of filters into a plurality of the sub-filters according to the plurality of channel groups; and assigning the plurality of sub-tensors and the plurality of sub-filters to a plurality of processors for parallel convolution processing.

Method and system for balanced-weight sparse convolution processing

Aspects of the present disclosure involve a system comprising a storage medium storing a program and method for receiving a video comprising a plurality of video segments; selecting a target action sequence that includes a sequence of action phases; receiving features of each of the video segments; computing, based on the received features, for each of the plurality of video segments, a plurality of action phase confidence scores indicating a likelihood that a given video segment includes a given action phase of the sequence of action phases; identifying a set of consecutive video segments of the plurality of video segments that corresponds to the target action sequence, wherein video segments in the set of consecutive video segments are arranged according to the sequence of action phases; and generating a display of the video that includes the set of consecutive video segments and skips other video segments in the video.

Segment action detection

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for few-shot learning-based generator training are disclosed. An exemplary method may start with obtaining a teacher model and a plurality of training samples, as well as a generator for generating more training samples. After generating a plurality of additional training samples using the method may continue with feeding the plurality of generated additional training samples into the teacher model to obtain a plurality of first statistics; and feeding the plurality of training samples into the teacher model to obtain a plurality second statistics. Then the method further includes training the generator to minimize a distance between the plurality of first statistics and the plurality of second statistics.

System and method for training sample generator with few-shot learning

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for few-shot learning-based generator training based on raw data collected from a specific domain or class. In cases where the raw data is collected from multiple domains but is not easily divisible into classes, the invention describes training multiple generators based on a pivot-sample-based training process. Pivot samples are randomly selected from the raw data for clustering, and each cluster of raw data may be used to train a generator using the few-shot learning-based training process.

System and method for pivot-sample-based generator training

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for optimizing neural network training, are described. The method may include: during a forward propagation at a current layer of a neural network, generating, based on a sparse input tensor and a sparse weight tensor of the current layer, a dense output tensor, and sparsifying the dense output tensor to obtain a sparse output tensor; during a backward propagation at the current layer of the neural network: determining a first sparse derivative tensor based on the sparse output tensor, obtaining a dense derivative tensor based on the first sparse derivative tensor and the sparse weight tensor of the current layer, and sparsifying the dense derivative tensor to obtain a second sparse derivative tensor; and training weight tensors of the neural network based on the first sparse derivative tensor and the second sparse derivative tensor.

System and method for bank-balanced sparse activation and joint-activation-weight-sparse training of neural networks

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for domain-specific pruning of neural networks are described. An exemplary method includes obtaining a first neural network trained based on a first training dataset; obtaining one or more second training datasets respectively from one or more domains; and training, based on the first neural network and the one or more second training datasets, a second neural network comprising the first neural network and one or more branches extended from the first neural network, wherein the second neural network is applicable for inferencing in the one or more domains, and the training comprises: training the one or more branches based respectively on the one or more second training datasets and an output of the first neural network.

System and method for domain specific neural network pruning

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for knowledge-preserving sparse pruning on neural networks are described. An exemplary method includes obtaining a pre-trained machine learning model trained based on a plurality of general-purpose training data; training a task-specific machine learning model by tuning the pre-trained machine learning model based on a plurality of task-specific training data corresponding to a task; constructing a student network based on the task-specific machine learning model; simultaneously performing (1) knowledge distillation from the trained task-specific machine learning model as a teacher network to the student network and (2) network pruning on the student network; and obtaining the trained student network for serving the task.

Growing community of inventors

Los Altos, CA, United States of America

Enxu Yan