v320: Proceedings of Analytical Connectionism 2026

2026-06-04 · Source: Proceedings of Machine Learning Research · Field: Science & Research — Artificial Intelligence & Machine Learning, Life Sciences & Biology, Social Sciences & Behavioral Studies · Depth: Expert, quick

Summary

Volume 320 of the Proceedings of the Analytical Connectionism Schools 2023-2024 compiles ten research papers presented at the school held from 1-31 December 2024 in London, UK, and New York, USA. Edited by Stefano Sarao Mannelli, Francesca Mignacco, Chi-Ning Chou, SueYeon Chung, and Andrew Saxe, this collection explores diverse aspects of connectionism and neural computation. Key topics include models of attractor dynamics in the brain, the statistical physics of machine learning, and connectionist theories of semantic cognition. Further contributions delve into the impact of representation sharing on parallel processing in neural networks, computational modeling of reinforcement learning, and the role of natural image statistics in visual representation. The volume also examines unifying neural population dynamics, the statistics of natural experience, and a computational basis of natural intelligence, alongside lecture notes on the dynamic hippocampus.

Key takeaway

For research scientists exploring the foundational links between neuroscience and artificial intelligence, this volume offers a comprehensive snapshot of current connectionist thought. You should review these proceedings to identify emerging research directions in areas like brain attractor dynamics, statistical physics of neural networks, and computational models of natural intelligence. Consider these diverse perspectives to inform your own research questions and potential interdisciplinary collaborations.

Key insights

The Analytical Connectionism Schools proceedings highlight diverse research at the intersection of neuroscience and machine learning.

Topics

• Connectionism
• Neural Networks
• Brain Dynamics
• Statistical Physics
• Semantic Cognition
• Reinforcement Learning

Best for: AI Scientist, Research Scientist, AI Student

Related on AIssential

• Quick Paper Review: "There Will Be a Scientific Theory of Deep Learning" — Learning mechanics, a theory of deep learning training dynamics, is proposed as an emerging scientific framework.
• Welcome to The Computist Journal - 2026 Update — The Computist Journal expands its 2026 scope to foundational computer science, algorithm design, and AI, offering free educational content.
• Statistics of correlations in nonlinear recurrent neural networks — A path-integral framework accurately computes correlation statistics in nonlinear RNNs, resolving linear model instabilities.
• KAST-BAR: Knowledge-Anchored Semantically-Dynamic Topology Brain Autoregressive Modeling for Universal Neural Interpretation — KAST-BAR aligns multi-level brain topology with expert semantic space to enhance EEG foundation models.
• The next paradigm: AI, Neural Networks, the Symbolic Brain — Current neural networks are fundamentally limited; a new symbolic brain paradigm is needed.
• Chaotic Oscillator Networks for Classification Tasks — Machine learning can approximate coupling terms in chaotic oscillator networks for scalable, efficient classification and pattern recognition.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Proceedings of Machine Learning Research.