Bottom-up and top-down approaches for the design of neuromorphic processing systems: tradeoffs and synergies between natural and artificial intelligence
While Moore's law has driven exponential computing power expectations, its nearing end
calls for new avenues for improving the overall system performance. One of these avenues …
calls for new avenues for improving the overall system performance. One of these avenues …
Desiderata for normative models of synaptic plasticity
C Bredenberg, C Savin - Neural Computation, 2024 - direct.mit.edu
Normative models of synaptic plasticity use computational rationales to arrive at predictions
of behavioral and network-level adaptive phenomena. In recent years, there has been an …
of behavioral and network-level adaptive phenomena. In recent years, there has been an …
Training end-to-end analog neural networks with equilibrium propagation
We introduce a principled method to train end-to-end analog neural networks by stochastic
gradient descent. In these analog neural networks, the weights to be adjusted are …
gradient descent. In these analog neural networks, the weights to be adjusted are …
Bottom-up and top-down neural processing systems design: Neuromorphic intelligence as the convergence of natural and artificial intelligence
While Moore's law has driven exponential computing power expectations, its nearing end
calls for new avenues for improving the overall system performance. One of these avenues …
calls for new avenues for improving the overall system performance. One of these avenues …
[HTML][HTML] Scaling equilibrium propagation to deep convnets by drastically reducing its gradient estimator bias
Equilibrium Propagation is a biologically-inspired algorithm that trains convergent recurrent
neural networks with a local learning rule. This approach constitutes a major lead to allow …
neural networks with a local learning rule. This approach constitutes a major lead to allow …
[HTML][HTML] Eqspike: spike-driven equilibrium propagation for neuromorphic implementations
Finding spike-based learning algorithms that can be implemented within the local
constraints of neuromorphic systems, while achieving high accuracy, remains a formidable …
constraints of neuromorphic systems, while achieving high accuracy, remains a formidable …
Physical learning beyond the quasistatic limit
Physical networks, such as biological neural networks, can learn desired functions without a
central processor, using local learning rules in space and time to learn in a fully distributed …
central processor, using local learning rules in space and time to learn in a fully distributed …
[HTML][HTML] Memristor crossbar circuits implementing equilibrium propagation for on-device learning
S Oh, J An, S Cho, R Yoon, KS Min - Micromachines, 2023 - mdpi.com
Equilibrium propagation (EP) has been proposed recently as a new neural network training
algorithm based on a local learning concept, where only local information is used to …
algorithm based on a local learning concept, where only local information is used to …
Backpropagation at the infinitesimal inference limit of energy-based models: Unifying predictive coding, equilibrium propagation, and contrastive hebbian learning
How the brain performs credit assignment is a fundamental unsolved problem in
neuroscience. Manybiologically plausible'algorithms have been proposed, which compute …
neuroscience. Manybiologically plausible'algorithms have been proposed, which compute …
Constrained predictive coding as a biologically plausible model of the cortical hierarchy
Predictive coding (PC) has emerged as an influential normative model of neural
computation with numerous extensions and applications. As such, much effort has been put …
computation with numerous extensions and applications. As such, much effort has been put …