How learning unfolds in the brain: toward an optimization view
How do changes in the brain lead to learning? To answer this question, consider an artificial
neural network (ANN), where learning proceeds by optimizing a given objective or cost …
neural network (ANN), where learning proceeds by optimizing a given objective or cost …
The computational and learning benefits of Daleian neural networks
A Haber, E Schneidman - Advances in Neural Information …, 2022 - proceedings.neurips.cc
Dale's principle implies that biological neural networks are composed of neurons that are
either excitatory or inhibitory. While the number of possible architectures of such Daleian …
either excitatory or inhibitory. While the number of possible architectures of such Daleian …
Neuronal diversity can improve machine learning for physics and beyond
Diversity conveys advantages in nature, yet homogeneous neurons typically comprise the
layers of artificial neural networks. Here we construct neural networks from neurons that …
layers of artificial neural networks. Here we construct neural networks from neurons that …
[PDF][PDF] The geometry of neural population activity during motor learning and memory
D Losey - 2023 - kilthub.cmu.edu
The human brain is a marvel of complexity, with billions of neurons and trillions of
connections that allow us to perform an astounding array of behaviors, from basic …
connections that allow us to perform an astounding array of behaviors, from basic …
The tuning of tuning: How adaptation influences single cell information transfer
F Zeldenrust, N Calcini, X Yan, A Bijlsma… - PLOS Computational …, 2024 - journals.plos.org
Sensory neurons reconstruct the world from action potentials (spikes) impinging on them. To
effectively transfer information about the stimulus to the next processing level, a neuron …
effectively transfer information about the stimulus to the next processing level, a neuron …
[PDF][PDF] Neural networks embrace learned diversity.
Diversity conveys advantages in nature, yet homogeneous neurons typically comprise the
layers of artificial neural networks. Here we construct neural networks from neurons that …
layers of artificial neural networks. Here we construct neural networks from neurons that …