Neural network pruning typically removes connections or neurons from a pretrained
converged model; while a new pruning paradigm, pruning at initialization (PaI), attempts to …

As neural network model sizes have dramatically increased, so has the interest in various
techniques to reduce their parameter counts and accelerate their execution. An active area …

Recent researches on neural network have shown significant advantage in machine
learning over traditional algorithms based on handcrafted features and models. Neural …

This paper aims at accelerating and compressing deep neural networks to deploy CNN
models into small devices like mobile phones or embedded gadgets. We focus on filter level …

Pruning has become a very powerful and effective technique to compress and accelerate
modern neural networks. Existing pruning methods can be grouped into two categories: filter …

The deployment constraints in practical applications necessitate the pruning of large-scale
deep learning models, ie, promoting their weight sparsity. As illustrated by the Lottery Ticket …

This article focuses on filter-level network pruning. A novel pruning method, termed CLR-
RNF, is proposed. We first reveal a “long-tail” pruning problem in magnitude-based weight …

Computing-in-Memory (CIM) is a promising solution for energy-efficient neural network (NN)
processors. Previous CIM chips [1],[4] mainly focus on the memory macro itself, lacking …

With the large number of antennas and subcarriers the overhead due to pilot transmission
for channel estimation can be prohibitive in wideband massive multiple-input multiple-output …

We introduce channel permutations as a method to maximize the accuracy of N: M sparse
networks. N: M sparsity requires N out of M consecutive elements to be zero and has been …