Related papers: Sorted Weight Sectioning for Energy-Efficient Unst…

Deep Neural Network (DNN) is powerful but computationally expensive and memory intensive, thus impeding its practical usage on resource-constrained front-end devices. DNN pruning is an approach for deep model compression, which aims at…

Nowadays, data are generated massively and rapidly from scientific fields as bioinformatics, neuroscience and astronomy to business and engineering fields. Cluster analysis, as one of the major data analysis tools, is therefore more…

This paper proposes a novel, efficient transfer learning method, called Scalable Weight Reparametrization (SWR) that is efficient and effective for multiple downstream tasks. Efficient transfer learning involves utilizing a pre-trained…

Deep neural networks (DNNs) are nowadays witnessing a major success in solving many pattern recognition tasks including skeleton-based classification. The deployment of DNNs on edge-devices, endowed with limited time and memory resources,…

Compressive Sensing (CS) method is a burgeoning technique being applied to diverse areas including wireless sensor networks (WSNs). In WSNs, it has been studied in the context of data gathering and aggregation, particularly aimed at…

Spiking neural network (SNN) is a brain-inspired model which has more spatio-temporal information processing capacity and computational energy efficiency. However, with the increasing depth of SNNs, the memory problem caused by the weights…

Deep neural networks for image super-resolution (SR) have demonstrated superior performance. However, the large memory and computation consumption hinders their deployment on resource-constrained devices. Binary neural networks (BNNs),…

Introduced in the late 1980s for generalization purposes, pruning has now become a staple for compressing deep neural networks. Despite many innovations in recent decades, pruning approaches still face core issues that hinder their…

This paper introduces neural architecture search (NAS) for the automatic discovery of small models for keyword spotting (KWS) in limited resource environments. We employ a differentiable NAS approach to optimize the structure of…

Weight quantization is used to deploy high-performance deep learning models on resource-limited hardware, enabling the use of low-precision integers for storage and computation. Spiking neural networks (SNNs) share the goal of enhancing…

Spiking Neural Networks (SNNs), with their inherent recurrence, offer an efficient method for processing the asynchronous temporal data generated by Dynamic Vision Sensors (DVS), making them well-suited for event-based vision applications.…

As a result of the growing size of Deep Neural Networks (DNNs), the gap to hardware capabilities in terms of memory and compute increases. To effectively compress DNNs, quantization and connection pruning are usually considered. However,…

Artificial Neural Networks (ANNs) have found widespread applications in tasks such as pattern recognition and image classification. However, hardware implementations of ANNs using conventional binary arithmetic units are computationally…

Energy efficiency is a crucial performance metric in sensor networks, directly determining the network lifetime. Consequently, a key factor in WSN is to improve overall energy efficiency to extend the network lifetime. Although many…

Recent advances in convolutional neural networks(CNNs) usually come with the expense of excessive computational overhead and memory footprint. Network compression aims to alleviate this issue by training compact models with comparable…

Memristor based neural networks have great potentials in on-chip neuromorphic computing systems due to the fast computation and low-energy consumption. However, the imprecise properties of existing memristor devices generally result in…

Model compression techniques, such as pruning and quantization, are becoming increasingly important to reduce the memory footprints and the amount of computations. Despite model size reduction, achieving performance enhancement on devices…

Computing-in-memory (CIM) has attracted significant attentions in recent years due to its massive parallelism and low power consumption. However, current CIM designs suffer from large area overhead of small CIM macros and bad programmablity…

The energy consumed by running large deep neural networks (DNNs) on hardware accelerators is dominated by the need for lots of fast memory to store both states and weights. This large required memory is currently only economically viable…

Architectures that incorporate Computing-in-Memory (CiM) using emerging non-volatile memory (NVM) devices have become strong contenders for deep neural network (DNN) acceleration due to their impressive energy efficiency. Yet, a significant…