Ultra-Low-Energy Mixed-Signal IC Implementing Encoded Neural Networks
Authors:
- 12 September 2016
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 63 (11) , 1974-1985
Abstract
Encoded Neural Networks (ENNs) associate low-complexity algorithm with a storage capacity much larger than Hopfield Neural Networks (HNNs) for the same number of nodes. Moreover, they have a lower density than HNNs in terms of connections, allowing a low-complexity circuit integration. The implementation of such a network requires low-complexity elements to take complete advantage of the assets of the model. This paper proposes an analog implementation of the ENNs. It is shown that this type of implementation is suitable for building network of thousands of nodes. To validate the proposed implementation, a prototype ENN of 30 computation nodes is designed, fabricated and tested on-chip for the ST 65-nm 1-V supply complementary metal-oxide silicon (CMOS) process. The circuit shows decoding performance similar to that of the theoretical model, and decodes a message in 58 ns. Moreover, the entire network occupies a silicon area of 16470 μm 2 and consumes 145 μW, yielding a measured energy consumption per synaptic event per computation node of 68 fJ.Keywords
Funding Information
- European Research Council (ERC-AdG2011, 290901 NEUCOD)
This publication has 29 references indexed in Scilit:
- A CMOS Spiking Neuron for Brain-Inspired Neural Networks With Resistive Synapses and In Situ LearningIEEE Transactions on Circuits and Systems II: Express Briefs, 2015
- Analog implementation of encoded neural networks2013
- SWIFT: A Low-Power Network-On-Chip Implementing the Token Flow Control Router Architecture With Swing-Reduced InterconnectsIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2012
- A New Formulation for Feedforward Neural NetworksIEEE Transactions on Neural Networks, 2011
- Comparison Between Analog and Digital Neural Network Implementations for Range-Finding ApplicationsIEEE Transactions on Neural Networks, 2009
- Synchrony Detection and Amplification by Silicon Neurons With STDP SynapsesIEEE Transactions on Neural Networks, 2004
- Analog implementation of ann with inherent quadratic nonlinearity of the synapsesIEEE Transactions on Neural Networks, 2003
- Learning capability and storage capacity of two-hidden-layer feedforward networksIEEE Transactions on Neural Networks, 2003
- An easy-to-use mismatch model for the MOS transistorIEEE Journal of Solid-State Circuits, 2002
- Digitally programmable analog building blocks for the implementation of artificial neural networksIEEE Transactions on Neural Networks, 1996