Learning probabilistic neural representations with randomly connected circuits
From MaRDI portal
Publication:5073175
Recommendations
- Bayesian Spiking Neurons II: Learning
- Probabilistic inference of binary Markov random fields in spiking neural networks through mean-field approximation
- Learning spatiotemporally encoded pattern transformations in structured spiking neural networks
- On the Maximization of Information Flow Between Spiking Neurons
- A learning framework for winner-take-all networks with stochastic synapses
Cites work
- scientific article; zbMATH DE number 3850830 (Why is no real title available?)
- A neural data structure for novelty detection
- Compressed sensing with coherent and redundant dictionaries
- Dynamic Analysis of Neural Encoding by Point Process Adaptive Filtering
- Evidence, information, and surprise
- Information Theory and Statistical Mechanics
- Neural networks and physical systems with emergent collective computational abilities
- Reducing the Dimensionality of Data with Neural Networks
Cited in
(5)- Probabilistic inference of binary Markov random fields in spiking neural networks through mean-field approximation
- Neural circuits trained with standard reinforcement learning can accumulate probabilistic information during decision making
- A learning framework for winner-take-all networks with stochastic synapses
- Predictive coding, variational autoencoders, and biological connections
- A neuroscience-inspired spiking neural network for EEG-based auditory spatial attention detection
This page was built for publication: Learning probabilistic neural representations with randomly connected circuits
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5073175)
