Abstract: A method for generating a sparse representation of a group of neural network features, the method includes (i) obtaining a group of neural network features (NNFs); and (ii) generating a lossless and sparse representation of the group of NNF, wherein the generating includes: (a) determining, by an allocation unit and based on one or more attributes of the group of NNFs, one or more relevant sparse representation generators (SRGs) out of a set of SRGs; (b) generating, by the one or more relevant SRGs, one or more relevant sparse outputs; (c) processing the one or more relevant sparse outputs to provide the lossless and sparse representation of the group of NNFs; and (d) outputting the lossless and sparse representation of the group of NNFs.

Abstract: A method for passive readout, the method may include (i) obtaining a group of descriptors that were outputted by of one or more neural network layers; wherein descriptors of the group of descriptors comprise a first number (N1) of descriptor elements; and (ii) generating a lossless and sparse representation of the group of descriptors. The generating may include (a) applying a dimension expanding convolution operation on the group of descriptors to provide a group of expanded descriptors; wherein expanded descriptors of the group of expanded descriptors comprises a second number (N2) of expanded descriptor elements, wherein N2 exceeds N1; and (b) quantizing the group of expanded descriptors to provide a group of binary descriptors that form a lossless and a sparse representation of the group of descriptors.

Abstract: A method for generating a sparse binary representation (SBR) of neural network intermediate features (NNIFs) of a neural network (NN). The method includes (i) feeding the neural network by input information; (ii) neural network processing the input information to provide, at least, the NNIFs; (iii) SBR processing, by a SBR module, the NNIFs, to provide the SBR representation of the NNIFs; and (iv) outputting the SBR representation. The SBR module has undergone a training process that used a loss function that takes into account a sparsity of training process SBR representations.