40 citations · 74 across the 11 of their papers we have counts for
11 papers
DeepFire2: A Convolutional Spiking Neural Network Accelerator on FPGAs
Myat Thu Linn Aung, Daniel Gerlinghoff, Chuping Qu +5
Brain-inspired spiking neural networks (SNNs) replace the multiply-accumulate operations of traditional neural networks by integrate-and-fire neurons, with the goal of achieving gr…
Hierarchical Weight Averaging for Deep Neural Networks
Xiaozhe Gu, Zixun Zhang, Yuncheng Jiang +4
Despite the simplicity, stochastic gradient descent (SGD)-like algorithms are successful in training deep neural networks (DNNs). Among various attempts to improve SGD, weight aver…
Desire Backpropagation: A Lightweight Training Algorithm for Multi-Layer Spiking Neural Networks based on Spike-Timing-Dependent Plasticity
Daniel Gerlinghoff, Tao Luo, Rick Siow Mong Goh +1
Spiking neural networks (SNNs) are a viable alternative to conventional artificial neural networks when resource efficiency and computational complexity are of importance. A major…
Statistical Modeling of Soft Error Influence on Neural Networks
Haitong Huang, Xinghua Xue, Cheng Liu +5
Soft errors in large VLSI circuits pose dramatic influence on computing- and memory-intensive neural network (NN) processing. Understanding the influence of soft errors on NNs is c…
Benchmarking Quantum(-inspired) Annealing Hardware on Practical Use Cases
Tian Huang, Jun Xu, Tao Luo +3
Quantum(-inspired) annealers show promise in solving combinatorial optimisation problems in practice. There has been extensive researches demonstrating the utility of D-Wave quantu…
E3NE: An End-to-End Framework for Accelerating Spiking Neural Networks with Emerging Neural Encoding on FPGAs
Daniel Gerlinghoff, Zhehui Wang, Xiaozhe Gu +2
Compiler frameworks are crucial for the widespread use of FPGA-based deep learning accelerators. They allow researchers and developers, who are not familiar with hardware engineeri…
DTNN: Energy-efficient Inference with Dendrite Tree Inspired Neural Networks for Edge Vision Applications
Tao Luo, Wai Teng Tang, Matthew Kay Fei Lee +3
Deep neural networks (DNN) have achieved remarkable success in computer vision (CV). However, training and inference of DNN models are both memory and computation intensive, incurr…
Efficient Spiking Neural Networks with Radix Encoding
Zhehui Wang, Xiaozhe Gu, Rick Goh +2
Spiking neural networks (SNNs) have advantages in latency and energy efficiency over traditional artificial neural networks (ANNs) due to its event-driven computation mechanism and…
RCT: Resource Constrained Training for Edge AI
Tian Huang, Tao Luo, Ming Yan +2
Neural networks training on edge terminals is essential for edge AI computing, which needs to be adaptive to evolving environment. Quantised models can efficiently run on edge devi…
Adaptive Precision Training for Resource Constrained Devices
Tian Huang, Tao Luo, Joey Tianyi Zhou
Learn in-situ is a growing trend for Edge AI. Training deep neural network (DNN) on edge devices is challenging because both energy and memory are constrained. Low precision traini…
EDCompress: Energy-Aware Model Compression for Dataflows
Zhehui Wang, Tao Luo, Joey Tianyi Zhou +1
Edge devices demand low energy consumption, cost and small form factor. To efficiently deploy convolutional neural network (CNN) models on edge device, energy-aware model compressi…