A correlation game for unsupervised learning yields computational interpretations of Hebbian excitation, anti-Hebbian inhibition, and synapse elimination.
H. Sebastian SeungJonathan ZungPublished in: CoRR (2017)
Keyphrases
- unsupervised learning
- learning rules
- associative memory
- biologically inspired
- hebbian learning
- supervised learning
- synaptic weights
- deep learning
- lateral inhibition
- neural network
- game theory
- receptive fields
- dimensionality reduction
- artificial neural networks
- computer games
- back propagation
- semi supervised
- learning scheme
- correlation coefficient
- game theoretic
- game playing
- game design
- video games
- virtual world
- feature extraction
- machine learning