Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Mixed-signal implementation of feedback-control optimizer for single-layer Spiking Neural Networks
Jonathan Haag, Christian Metzner, Dmitrii Zendrikov +4
On-chip learning is key to scalable and adaptive neuromorphic systems, yet existing training methods are either difficult to implement in hardware or overly restrictive. However, r…
cs.LG2025
Mechanistic Interpretability of RNNs emulating Hidden Markov Models
Elia Torre, Michele Viscione, Lucas Pompe +2
Recurrent neural networks (RNNs) provide a powerful approach in neuroscience to infer latent dynamics in neural populations and to generate hypotheses about the neural computations…