Approximate computation of post-synaptic spikes reduces bandwidth to synaptic storage in a model of cortex

• The Bayesian Confidence Propagation Neural Network (BCPNN) is a spiking model of the cortex. The synaptic weights of BCPNN are organized as matrices. They require substantial synaptic storage and a large bandwidth to it. The algorithm requires a dual access pattern to these matrices, both row-wise and column-wise, to access its synaptic weights. In this work, we exploit an algorithmic optimization that eliminates the column-wise accesses. The new computation model approximates the post-synaptic spikes computation with the use of a predictor. We have adopted this approximate computational model to improve upon the previously reported ASIC implementation, called eBrainII. We also present the error analysis of the approximation to show that it is negligible. The reduction in storage and bandwidth to the synaptic storage results in a 48% reduction in energy compared to eBrainII. The reported approximation method also applies to other neural network models based on a Hebbian learning rule.

Ämnesord

NATURVETENSKAP  -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)

NATURAL SCIENCES  -- Computer and Information Sciences -- Computer Sciences (hsv//eng)

Nyckelord

3D DRAM

Approximate computing

ASIC

Bandwidth optimization

Neuromorphic Hardware

Backpropagation

Bandwidth

Computation theory

Matrix algebra

Access patterns

Algorithmic optimization

Approximate computation

Approximation methods

Computation model

Computational model

Hebbian learning

Neural network model

Neural networks

Publikations- och innehållstyp

ref (ämneskategori)

kon (ämneskategori)