Connectome-based reservoir computing with the conn2res toolbox
The connection patterns of neural circuits form a complex network. How signaling in these
circuits manifests as complex cognition and adaptive behaviour remains the central question …
circuits manifests as complex cognition and adaptive behaviour remains the central question …
Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules
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 …
gradient descent algorithms for training recurrent neural networks (RNNs). Yet, beyond task …
Probing learning through the lens of changes in circuit dynamics
O Marschall, C Savin - bioRxiv, 2023 - biorxiv.org
Despite the success of dynamical systems as accounts of circuit computation and observed
behavior, our understanding of how dynamical systems evolve over learning is very limited …
behavior, our understanding of how dynamical systems evolve over learning is very limited …
A Minimal “Functionally Sentient” Organism Trained With Backpropagation Through Time
M Pisheh Var, M Fairbank… - Adaptive Behavior, 2023 - journals.sagepub.com
This article presents a scenario where a simple simulated organism must explore and
exploit an environment containing a food pile. The organism learns to make observations of …
exploit an environment containing a food pile. The organism learns to make observations of …
conn2res: A toolbox for connectome-based reservoir computing
The connection patterns of neural circuits form a complex network. How signaling in these
circuits manifests as complex cognition and adaptive behaviour remains the central question …
circuits manifests as complex cognition and adaptive behaviour remains the central question …
BP (\lambda): Online Learning via Synthetic Gradients
J Pemberton, RP Costa - arXiv preprint arXiv:2401.07044, 2024 - arxiv.org
Training recurrent neural networks typically relies on backpropagation through time (BPTT).
BPTT depends on forward and backward passes to be completed, rendering the network …
BPTT depends on forward and backward passes to be completed, rendering the network …
[HTML][HTML] Transition to chaos separates learning regimes and relates to measure of consciousness in recurrent neural networks
Recurrent neural networks exhibit chaotic dynamics when the variance in their connection
strengths exceed a critical value. Recent work indicates connection variance also modulates …
strengths exceed a critical value. Recent work indicates connection variance also modulates …
How Initial Connectivity Shapes Biologically Plausible Learning in Recurrent Neural Networks
W Liu, X Zhang, YH Liu - arXiv preprint arXiv:2410.11164, 2024 - arxiv.org
The impact of initial connectivity on learning has been extensively studied in the context of
backpropagation-based gradient descent, but it remains largely underexplored in …
backpropagation-based gradient descent, but it remains largely underexplored in …
Flexible cognition in context-modulated reservoir networks
The brains of all animals are plastic, allowing us to form new memories, adapt to new
environments, and to learn new tasks. What is less clear is how much plasticity is required to …
environments, and to learn new tasks. What is less clear is how much plasticity is required to …
conn2res: A toolbox for connectome-based reservoir computing
The connection patterns of neural circuits form a complex network. How signaling in these
circuits manifests as complex cognition and adaptive behaviour remains the central question …
circuits manifests as complex cognition and adaptive behaviour remains the central question …