Kanaka Rajan

InputDSA: Demixing, then comparing recurrent and externally driven dynamics

Memories to Maps: Mechanisms of In-Context Reinforcement Learning in Transformers

Dissecting Larval Zebrafish Hunting Behavior using Deep Reinforcement Learning trained RNNs

A dimensional R2 regression metric

Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural Networks

Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules

POCO: Scalable Neural Forecasting through Population Conditioning

Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments

Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural Networks