Large-scale, highly integrated and low-power-consuming hardware is becoming
progressively more important for realizing optical neural networks (ONNs) capable of …

Large-scale deep neural networks (DNNs) are both compute and memory intensive. As the
size of DNNs continues to grow, it is critical to improve the energy efficiency and …

In natural language processing (NLP), the" Transformer" architecture was proposed as the
first transduction model replying entirely on self-attention mechanisms without using …

Recently, significant accuracy improvement has been achieved for acoustic recognition
systems by increasing the model size of Long Short-Term Memory (LSTM) networks …

Deep neural networks (DNNs), as the basis of object detection, will play a key role in the
development of future autonomous systems with full autonomy. The autonomous systems …

Recurrent Neural Networks (RNNs) are becoming increasingly important for time series-
related applications which require efficient and real-time implementations. The two major …

We present an efficient coresets-based neural network compression algorithm that sparsifies
the parameters of a trained fully-connected neural network in a manner that provably …

Weight pruning methods of deep neural networks (DNNs) have been demonstrated to
achieve a good model pruning ratio without loss of accuracy, thereby alleviating the …

Weight pruning methods of deep neural networks (DNNs) have been demonstrated to
achieve a good model pruning rate without loss of accuracy, thereby alleviating the …

Many model compression techniques of Deep Neural Networks (DNNs) have been
investigated, including weight pruning, weight clustering and quantization, etc. Weight …