Picture for Anand Subramoney

Anand Subramoney

State-space models can learn in-context by gradient descent

Add code
Oct 15, 2024
Viaarxiv icon

Exploring the limits of Hierarchical World Models in Reinforcement Learning

Add code
Jun 01, 2024
Viaarxiv icon

Weight Sparsity Complements Activity Sparsity in Neuromorphic Language Models

Add code
May 01, 2024
Viaarxiv icon

Scalable Event-by-event Processing of Neuromorphic Sensory Signals With Deep State-Space Models

Add code
Apr 29, 2024
Viaarxiv icon

Language Modeling on a SpiNNaker 2 Neuromorphic Chip

Add code
Dec 14, 2023
Viaarxiv icon

Activity Sparsity Complements Weight Sparsity for Efficient RNN Inference

Add code
Nov 13, 2023
Viaarxiv icon

Beyond Weights: Deep learning in Spiking Neural Networks with pure synaptic-delay training

Add code
Jun 23, 2023
Viaarxiv icon

Block-local learning with probabilistic latent representations

Add code
May 24, 2023
Viaarxiv icon

Efficient Real Time Recurrent Learning through combined activity and parameter sparsity

Add code
Mar 10, 2023
Viaarxiv icon

EGRU: Event-based GRU for activity-sparse inference and learning

Add code
Jun 13, 2022
Figure 1 for EGRU: Event-based GRU for activity-sparse inference and learning
Figure 2 for EGRU: Event-based GRU for activity-sparse inference and learning
Figure 3 for EGRU: Event-based GRU for activity-sparse inference and learning
Figure 4 for EGRU: Event-based GRU for activity-sparse inference and learning
Viaarxiv icon