Neuromorphic architectures for spiking deep neural networks
Top Cited Papers
- 1 December 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4.2.1-4.2.4
Abstract
We present a full custom hardware implementation of a deep neural network, built using multiple neuromorphic VLSI devices that integrate analog neuron and synapse circuits together with digital asynchronous logic circuits. The deep network comprises an event-based convolutional stage for feature extraction connected to a spike-based learning stage for feature classification. We describe the properties of the chips used to implement the network and present preliminary experimental results that validate the approach proposed.Keywords
This publication has 14 references indexed in Scilit:
- Complex Learning in Bio-plausible Memristive NetworksScientific Reports, 2015
- Neuromorphic Electronic Circuits for Building Autonomous Cognitive SystemsProceedings of the IEEE, 2014
- Integration of nanoscale memristor synapses in neuromorphic computing architecturesNanotechnology, 2013
- A memory-efficient routing method for large-scale spiking neural networks2013
- An Electronic Synapse Device Based on Metal Oxide Resistive Switching Memory for Neuromorphic ComputationIEEE Transactions on Electron Devices, 2011
- Firing patterns in the adaptive exponential integrate-and-fire modelBiological Cybernetics, 2008
- A 128$\times$128 120 dB 15 $\mu$s Latency Asynchronous Temporal Contrast Vision SensorIEEE Journal of Solid-State Circuits, 2008
- Learning Real-World Stimuli in a Neural Network with Spike-Driven Synaptic DynamicsNeural Computation, 2007
- Adaptive Exponential Integrate-and-Fire Model as an Effective Description of Neuronal ActivityJournal of Neurophysiology, 2005
- Bagging predictorsMachine Learning, 1996