Edge of chaos and prediction of computational performance for neural circuit models

DOI10.1016/J.NEUNET.2007.04.017MaRDI QIDQ2373495zbMATH OpenOpenAlexWikidataFDO

Authors Robert A. Legenstein, Wolfgang Maass

Publication date 11 July 2007

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2007.04.017

zbMATH Keywords

computational performanceneural networksnetwork dynamicsedge of chaosspiking networksmicrocircuits

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Performance evaluation, queueing, and scheduling in the context of computer systems (68M20)

Recommendations

• Real-Time Computation at the Edge of Chaos in Recurrent Neural Networks
• Do reservoir computers work best at the edge of chaos?
• ATTENTION-LOCKED COMPUTATION WITH CHAOTIC NEURAL NETS
• On the computational power of circuits of spiking neurons
• Local activity in CNN with dynamic memory synapses

Cites work

• scientific article; zbMATH DE number 711298 (Why is no real title available?)
• scientific article; zbMATH DE number 1042219 (Why is no real title available?)
• scientific article; zbMATH DE number 1497419 (Why is no real title available?)
• scientific article; zbMATH DE number 1391397 (Why is no real title available?)
• Analog computation via neural networks
• New directions in statistical signal processing: from systems to brain
• On the computational power of circuits of spiking neurons
• Real-Time Computation at the Edge of Chaos in Recurrent Neural Networks
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations

Cited in

(23)

• Randomly connected networks have short temporal memory
• Short-term memory capacity in networks via the restricted isometry property
• Functional echo state network for time series classification
• Chimera states in a ring of map-based neurons
• Frustration induced transient chaos, fractal and riddled basins in coupled limit cycle oscillators
• A substrate-independent framework to characterize reservoir computers
• Do reservoir computers work best at the edge of chaos?
• Reservoir computing with computational matter
• Dynamical criticality: overview and open questions
• Real-Time Computation at the Edge of Chaos in Recurrent Neural Networks
• Memory in linear recurrent neural networks in continuous time
• A theoretical basis for emergent pattern discrimination in neural systems through slow feature extraction
• Connectivity, dynamics, and memory in reservoir computing with binary and analog neurons
• Achieving criticality for reservoir computing using environment-induced explosive death
• Adaptive balancing of exploration and exploitation around the edge of chaos in internal-chaos-based learning
• Complex dynamics of a bi-directional N-type locally-active memristor
• Reservoir computing approaches to recurrent neural network training
• Reservoir computing quality: connectivity and topology
• The criticality hypothesis: how local cortical networks might optimize information processing
• A robust model of gated working memory
• Biological modelling of a computational spiking neural network with neuronal avalanches
• Symbolic computation using cellular automata-based hyperdimensional computing
• The reservoir's perspective on generalized synchronization

This page was built for publication: Edge of chaos and prediction of computational performance for neural circuit models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2373495)