Miguel Lazaro-Gredilla

Latest

• Space is a latent sequence: Structured sequence learning as a unified theory of representation in the hippocampus
• Clone-structured graph representations enable flexible learning and vicarious evaluation of cognitive maps
• A detailed mathematical theory of thalamic and cortical microcircuits based on inference in a generative vision model
• A Model of Fast Concept Inference with Object-Factorized Cognitive Programs
• Learning cognitive maps as structured graphs for vicarious evaluation
• Learning undirected models via query training
• Different clones for different contexts: Hippocampal cognitive maps as higher-order graphs of a cloned HMM
• Memorize-Generalize: An online algorithm for learning higher-order sequential structure with cloned Hidden Markov Models
• Learning higher-order sequential structure with cloned HMMs
• Beyond Imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs
• Cortical micro-circuits from a generative vision model
• Explaining Visual Cortex Phenomena using Recursive Cortical Network
• A generative model for vision that trains with high data efficiency and breaks text-based CAPTCHAs
• Schema Networks: Zero-shot transfer with a generative causal model of intuitive physics
• Hierarchical Compositional Feature Learning
• A generative model for vision
• Learning concepts as cognitive programs