Ryan Singh

Buckley Lab - Sussex University, Verses AI.

prof_pic.jpg

I am generally interested in ideas related to the Bayesian brain hypothesis; particularly predictive coding and active inference. More broadly, the use of Dynamical Systems and Information Theory to understand cognitive phenomena. I am especially interested in exploring how these can be used to understand the trade-offs inherent in decision making with constrained resources.

I am currently a PhD candidate under Christopher Buckley. Previously, I graduated from Wadham College, Oxford with undergraduate and masters degrees in Mathematics. I then worked for a small Machine Learning start up for a few years, before returning to study with a renewed interest in the intersection between machine learning and biological intelligence.

latest posts

May 01, 2024 Hello World

selected publications

  1. Hybrid Recurrent Models Support Emergent Descriptions for Hierarchical Planning and Control
    Poppy Collis, Ryan Singh, Paul Kinghorn, and 1 more author
    In ICML 2024 Workshop: Foundations of Reinforcement Learning and Control–Connections and Perspectives , 2024
  2. Collapsed Inference a Unifying Principle of Attention
    Ryan Singh, and Christopher L. Buckley
    In 2023 Conference on Cognitive Computational Neuroscience , 2023
  3. Attention as implicit structural inference
    Ryan Singh, and Christopher L. Buckley
    Advances in Neural Information Processing Systems, 2023
  4. Understanding predictive coding as an adaptive trust-region method
    Francesco Innocenti, Ryan Singh, and Christopher L. Buckley
    arXiv preprint arXiv:2305.18188, 2023