A reward-maximizing spiking neuron as a bounded rational decision maker

DOI10.1162/NECO_A_00758zbMATH Open1414.91112DBLPjournals/neco/LeibfriedB15WikidataQ35665009 ScholiaQ35665009MaRDI QIDQ5380302FDOQ5380302

Authors: Felix Leibfried, Daniel A. Braun 

Publication date: 4 June 2019

Published in: Neural Computation (Search for Journal in Brave)

Recommendations

• Thermodynamics as a theory of decision-making with information-processing costs
• Information-theoretic bounded rationality and \(\epsilon\)-optimality
• Optimal decision making on the basis of evidence represented in spike trains
• Rapid decision threshold modulation by reward rate in a neural network
• Metabolic cost of neuronal information in an empirical stimulus-response model

zbMATH Keywords

bounded rational decision makingreward-maximizing spiking neuron model

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Decision theory (91B06)

Cites Work

• Slice sampling. (With discussions and rejoinder)
• Elements of Information Theory
• Pattern recognition and machine learning.
• A Mathematical Theory of Communication
• Title not available (Why is that?)
• Quantal response equilibria for normal form games
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• An algorithm for computing the capacity of arbitrary discrete memoryless channels
• Computation of channel capacity and rate-distortion functions
• Efficient computation of optimal actions
• Optimal control as a graphical model inference problem
• Reinforcement learning. An introduction
• Information-theoretic bounded rationality and \(\epsilon\)-optimality
• Spike-Timing-Dependent Plasticity and Relevant Mutual Information Maximization
• Thermodynamics as a theory of decision-making with information-processing costs
• A simplified neuron model as a principal component analyzer
• Reinforcement Learning Through Modulation of Spike-Timing-Dependent Synaptic Plasticity
• Reinforcement Learning, Spike-Time-Dependent Plasticity, and the BCM Rule
• Optimal Spike-Timing-Dependent Plasticity for Precise Action Potential Firing in Supervised Learning
• Hierarchical relative entropy policy search
• Artificial general intelligence. 4th international conference, AGI 2011, Mountain View, CA, USA, August 3--6, 2011. Proceedings
• On the Maximization of Information Flow Between Spiking Neurons
• Spiking Neurons Can Learn to Solve Information Bottleneck Problems and Extract Independent Components
• Probabilistic choice and procedurally bounded rationality
• A Spiking Neuron as Information Bottleneck
• On the computation of rate-distortion functions (Corresp.)
• A Theory of the Epigenesis of Neuronal Networks by Selective Stabilization of Synapses
• Trading value and information in mdps

Cited In (2)

• Thermodynamics as a theory of decision-making with information-processing costs
• Bio-inspired feedback-circuit implementation of discrete, free energy optimizing, winner-take-all computations

This page was built for publication: A reward-maximizing spiking neuron as a bounded rational decision maker

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5380302)