This chapter reconstructs the McCulloch-Pitts program as a physics of neural computation, moving beyond the simplified view of binary neurons. It details how their 1943 logical calculus can be developed in both directions: characterizing propositions from network activity and constructing networks for given logical expressions. The work also explores their later research on cyclic preference, universals, and the frog retina, using modern mathematical tools to analyze invariant operations and the selectivity of neurons. AI
IMPACT Provides historical context for foundational concepts in neural computation and AI.
RANK_REASON This is a research paper published on arXiv detailing historical work in neural computation. [lever_c_demoted from research: ic=1 ai=1.0]
Read on arXiv cs.NE (Neural & Evolutionary) →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →