Artificial neural networks in hardware: A survey of two decades of progress

By Janardan Misra, Indranil Saha. Neurocomputing, 2010

616 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/36a44b761e553eaefc4053ce0172b43295049335

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Electrical and Electronic Engineering

Citations in the corpus

Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruption (2020, methodology): “For neural networks deployed in physical devices, advances in hardware neural networks (Feldmann et al. 2019; Misra and Saha 2010; Abdelsalam et al. 2018; Salimi-Nezhad et al. 2019; Weber, da Silva Labres, and Cabrera 2019; Bui and Phillips 2019) also call for study”
FINN: A Framework for Fast, Scalable Binarized Neural Network Inference (2016, methodology): “[16] J. Misra and I. Saha.”
X1000 real-time phoneme recognition VLSI using feed-forward deep neural networks (2014, background): “There are several, such as analog, digital, hybrid, and FPGA implementation approaches for neural networks [5, 6, 7, 8, 9, 10, 11].”
FPGA-Based Accelerators of Deep Learning Networks for Learning and Classification: A Review (2019, background): “However, they can achieve at least moderate performance with lower power consumption [62].”
Broadcast and Weight: An Integrated Network For Scalable Photonic Spike Processing (2014, background): “Unconventional hardware has a long history of massive parallelism, but a more recently recognized point of neural inspiration is a sparse coding scheme called spiking [1].”
When Neurons Fail (2017, background): “, to go for genuinely distributed neural networks [15].”
FINN-R (2018, methodology): “We refer the reader to the work by Misra and Saha [40] for a comprehensive survey.”
Recent Advances in Physical Reservoir Computing: A Review (2018, methodology): “For hardware implementation of normal RNNs where training is necessary, we often rely on advanced technologies of neural network hardware (Misra & Saha, 2010) and neuromorphic hardware (Hasler & Marr, 2013).”
The hardware lottery (2020, background): “In the late 1980/90s, the idea of specialized hardware for neural networks had passed the novelty stage (Misra & Saha, 2010; Lind-sey & Lindblad, 1994; Dean, 1990).”
Minitaur, an Event-Driven FPGA-Based Spiking Network Accelerator (2014, methodology): “Following [12], the connections per second, or more specifically, the PSCs/second, was chosen as the primary performance metric.”
On the Robustness of a Neural Network (2017, neutral): “, to go for genuinely distributed neural networks [10].”
When Neurons Fail - Technical Report (2016, background): “In particular, in the case of multilayer (often called deep) neural networks, our results provide a guidance on how to distribute synaptic weights over layers, and how to tune the neuron activation function to increase robustness.”