Lessons from Neuroscience for AI: How integrating Actions, Compositional Structure and Episodic Memory could enable Safe, Interpretable and Human-Like AI

Documenti analoghi

• Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neuroscience
  di: Vilas, Martina G., et al.
  Pubblicazione: (2024)
• A Biologically Interpretable Cognitive Architecture for Online Structuring of Episodic Memories into Cognitive Maps
  di: Dzhivelikian, E. A., et al.
  Pubblicazione: (2025)
• Active Predictive Coding: A Unified Neural Framework for Learning Hierarchical World Models for Perception and Planning
  di: Rao, Rajesh P. N., et al.
  Pubblicazione: (2022)
• Bridging Neuroscience and AI: Environmental Enrichment as a Model for Forward Knowledge Transfer
  di: Saxena, Rajat, et al.
  Pubblicazione: (2024)
• Reconstruction of Partial Dissimilarity Matrices for Cognitive Neuroscience
  di: Moerel, Denise, et al.
  Pubblicazione: (2025)