In theoretical neuroscience, recent work leverages deep learning tools to explore how some network attributes critically influence its learning dynamics. Notably, initial weight …
MÁ Luján, DP Covey, R Young-Morrison… - Nature …, 2023 - nature.com
Brain levels of the endocannabinoid 2-arachidonoylglycerol (2-AG) shape motivated behavior and nucleus accumbens (NAc) dopamine release. However, it is not clear whether …
R Engelken - Advances in Neural Information Processing …, 2023 - proceedings.neurips.cc
Abstract Spiking Neural Networks (SNNs) are biologically-inspired models that are capable of processing information in streams of action potentials. However, simulating and training …
AG Ororbia, MA Kelly - Proceedings of the AAAI Symposium Series, 2023 - ojs.aaai.org
Over the last few years, large neural generative models, capable of synthesizing semantically rich passages of text or producing complex images, have recently emerged as …
To unveil how the brain learns, ongoing work seeks biologically-plausible approximations of gradient descent algorithms for training recurrent neural networks (RNNs). Yet, beyond task …
Y Jiang, K Hu, T Zhang, H Gao, Y Liu… - The Twelfth …, 2024 - openreview.net
Spiking neural networks (SNNs) are energy-efficient and hold great potential for large-scale inference. Since training SNNs from scratch is costly and has limited performance …
Recurrent neural networks exhibit chaotic dynamics when the variance in their connection strengths exceed a critical value. Recent work indicates connection variance also modulates …
The goal of theoretical neuroscience is to develop models that help us better understand biological intelligence. Such models range broadly in complexity and biological detail. For …
Theoretical neuroscience has come to face a unique set of opportunities and challenges. By virtue of being at the nexus of experimental neurobiology and machine learning, theoretical …