Edge of Chaos Computation in Mixed-Mode VLSI - A Hard Liquid

Published 1 December 2004

Felix Schürmann, Karlheinz Meier, Johannes Schemmel

Citations34

TL;DR

Results of a software implementation of a hardware implemented neural network are reproduced showing that the performance peaks when the network exhibits dynamics at the edge of chaos.

Abstract

Computation without stable states is a computing paradigm different from Turing’s and has been demonstrated for various types of simulated neural networks. This publication transfers this to a hardware implemented neural network. Results of a software implementation are reproduced showing that the performance peaks when the network exhibits dynamics at the edge of chaos. The liquid computing approach seems well suited for operating analog computing devices such as the used VLSI neural network. 1

Keywords

Computer Science

Neural ComputationReal-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations

4,037 Citations2002Wolfgang Maass, Thomas Natschläger +1 more

A new computational model for real-time computing on time-varying input that provides an alternative to paradigms based on Turing machines or attractor neural networks, based on principles of high-dimensional dynamical systems in combination with statistical learning theory and can be implemented on generic evolved or found recurrent circuitry.

View PDF

IEEE Transactions on Electronic ComputersGeometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition

2,037 Citations1965Thomas M. Cover

It is shown that a family of surfaces having d degrees of freedom has a natural separating capacity of 2d pattern vectors, thus extending and unifying results of Winder and others on the pattern-separating capacity of hyperplanes.

Physica D Nonlinear PhenomenaComputation at the edge of chaos: Phase transitions and emergent computation

1,509 Citations1990Chris Langton

There is a fundamental connection between computation and phase transitions, especially second-order or “critical” transitions, and some of the implications for the understanding of nature if such a connection is borne out are discussed.

View PDF

Neural ComputationReal-Time Computation at the Edge of Chaos in Recurrent Neural Networks

846 Citations2004Nils Bertschinger, Thomas Natschläger

It is shown that only near the critical boundary can recurrent networks of threshold gates perform complex computations on time series, which strongly supports conjectures that dynamical systems that are capable of doing complex computational tasks should operate near the edge of chaos.

Analog Integrated Circuits and Signal ProcessingA Mixed-Mode Analog Neural Network Using Current-Steering Synapses

26 Citations2004Johannes Schemmel, Steffen Hohmann +2 more

A hardware neural network is presented that combines digital signalling with analog computing that allows a high amount of parallelism in the synapse operation while maintaining signal integrity and high transmission speed throughout the system.

Information Dynamics and Emergent Computation in Recurrent Circuits of Spiking Neurons

15 Citations2003Thomas Natschläger, Wolfgang Maass

It is shown that such recurrent circuits of spiking neurons have an inherent capability to carry out rapid computations on complex spike patterns, merging information contained in the order of spike arrival with previously acquired context information.

Training fast mixed-signal neural networks for data classification

4 Citations2005Steffen Hohmann, Johannes Fieres +4 more

It is shown that the presented training strategy is suited for use in conjunction with a specialized coprocessor that speeds up evolutionary algorithms by performing the genetic operations within a configurable logic.