Learning with “Relevance”: Using a Third Factor to Stabilize Hebbian Learning
From MaRDI portal
Recommendations
- Mathematical formulations of Hebbian learning
- Hebbian errors in learning: an analysis using the Oja model
- Stabilization of Hebbian neural nets by inhibitory learning
- Intrinsic stabilization of output rates by spike-based Hebbian learning
- Learning Only When Necessary: Better Memories of Correlated Patterns in Networks with Bounded Synapses
Cites work
- A simplified neuron model as a principal component analyzer
- How the Shape of Pre- and Postsynaptic Signals Can Influence STDP: A Biophysical Model
- ISO Learning Approximates a Solution to the Inverse-Controller Problem in an Unsupervised Behavioral Paradigm
- Isotropic Sequence Order Learning
- Strongly Improved Stability and Faster Convergence of Temporal Sequence Learning by Using Input Correlations Only
- Temporal difference model reproduces anticipatory neural activity
Cited in
(5)- Hebbian errors in learning: an analysis using the Oja model
- Mathematical formulations of Hebbian learning
- A Spiking Neural Network Model of an Actor-Critic Learning Agent
- On the Asymptotic Equivalence Between Differential Hebbian and Temporal Difference Learning
- Strongly Improved Stability and Faster Convergence of Temporal Sequence Learning by Using Input Correlations Only
This page was built for publication: Learning with “Relevance”: Using a Third Factor to Stabilize Hebbian Learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5441318)
