Brain-Like Stochastic Search: A Research Challenge and Funding Opportunity

2010/06/01 by Paul J. Werbos, Werbos, Paul J.
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #Optimization and Search Problems #Quantum Computing Algorithms and Architecture #cs.AI

paper · pdf · doi:10.48550/arxiv.1006.0385

Plenary talk at IEEE Conference on Evolutionary Computing 1999, extended in 2010 with new appendix

arxiv created 2010/06/01 · arxiv updated 2010/06/03

Abstract

Brain-Like Stochastic Search (BLiSS) refers to this task: given a family of utility functions U(u,A), where u is a vector of parameters or task descriptors, maximize or minimize U with respect to u, using networks (Option Nets) which input A and learn to generate good options u stochastically. This paper discusses why this is crucial to brain-like intelligence (an area funded by NSF) and to many applications, and discusses various possibilities for network design and training. The appendix discusses recent research, relations to work on stochastic optimization in operations research, and relations to engineering-based approaches to understanding neocortex.

Related

• Brain development dictates energy constraints on neural architecture search: cross-disciplinary insights on optimization strategies
• Simplex Search Based Brain Storm Optimization
• NOVAS: Non-convex Optimization via Adaptive Stochastic Search for End-to-End Learning and Control
• The brain as a probabilistic transducer: an evolutionarily plausible network architecture for knowledge representation, computation, and behavior
• ASBSO: An Improved Brain Storm Optimization With Flexible Search Length and Memory-Based Selection