[HTML][HTML] Fast burst fraction transients convey information independent of the firing rate
Theories of attention and learning have hypothesized a central role for high-frequency bursting
in cognitive functions, but experimental reports of burst-mediated representations in vivo …
in cognitive functions, but experimental reports of burst-mediated representations in vivo …
Towards a" universal translator" for neural dynamics at single-cell, single-spike resolution
Neuroscience research has made immense progress over the last decade, but our
understanding of the brain remains fragmented and piecemeal: the dream of probing an arbitrary …
understanding of the brain remains fragmented and piecemeal: the dream of probing an arbitrary …
Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL
In real life, success is often contingent upon multiple critical steps that are distant in time from
each other and from the final reward. These critical steps are challenging to identify with …
each other and from the final reward. These critical steps are challenging to identify with …
Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent
Understanding the mechanisms behind decisions taken by large foundation models in
sequential decision making tasks is critical to ensuring that such systems operate transparently …
sequential decision making tasks is critical to ensuring that such systems operate transparently …
Stimulus information guides the emergence of behavior-related signals in primary somatosensory cortex during learning
Neurons in the primary cortex carry sensory- and behavior-related information, but it remains
an open question how this information emerges and intersects together during learning. …
an open question how this information emerges and intersects together during learning. …
Towards alignment of Reinforcement Learning agents; for consideration of safety, robustness and fairness.
H Satija - 2024 - escholarship.mcgill.ca
Reinforcement Learning (RL) has emerged as the standard paradigm for sequential
decision-making and a framework for general intelligence. At its core, the RL problem is one of trial-…
decision-making and a framework for general intelligence. At its core, the RL problem is one of trial-…
Deep Learning Frameworks for Modeling How Neural Circuits Learn
YH Liu - 2024 - search.proquest.com
The brain’s prowess in learning and adapting remains an enigma, particularly in its approach
to the’temporal credit assignment’problem. How do neural circuits determine which …
to the’temporal credit assignment’problem. How do neural circuits determine which …
Thousands of AI authors on the future of AI
K Grace, H Stewart, JF Sandkühler, S Thomas… - arXiv preprint arXiv …, 2024 - arxiv.org
In the largest survey of its kind, 2,778 researchers who had published in top-tier artificial
intelligence (AI) venues gave predictions on the pace of AI progress and the nature and impacts …
intelligence (AI) venues gave predictions on the pace of AI progress and the nature and impacts …
Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis
A Meulemans, S Schug… - Advances in Neural …, 2024 - proceedings.neurips.cc
To make reinforcement learning more sample efficient, we need better credit assignment
methods that measure an action’s influence on future rewards. Building upon Hindsight Credit …
methods that measure an action’s influence on future rewards. Building upon Hindsight Credit …
Prediction and control in continual reinforcement learning
Temporal difference (TD) learning is often used to update the estimate of the value function
which is used by RL agents to extract useful policies. In this paper, we focus on value …
which is used by RL agents to extract useful policies. In this paper, we focus on value …