Learning sequence attractors in recurrent networks with hidden neurons
From MaRDI portal
(Redirected from Learning sequence attractors in recurrent networks with hidden neurons)
The authors consider recurrent networks motivated by temporal sequential activity in the brain. It is essential that the networks include hidden neurons for the sake of storing arbitrary pattern sequences. The networks are capable of learning sequence attractors which arise through the convergence of a local learning algorithm. Both synthetic and real-world datasets are used to train models which in turn store and retrieve pattern sequences robustly.
Recommendations
- Stimulus-Driven and Spontaneous Dynamics in Excitatory-Inhibitory Recurrent Neural Networks for Sequence Representation
- scientific article; zbMATH DE number 1928616
- A model for complex sequence learning and reproduction in neural populations
- A model cortical circuit for the storage of temporal sequences
- Networks that learn the precise timing of event sequences
Cites work
- Exponentially long orbits in Hopfield neural networks
- High-dimensional probability. An introduction with applications in data science
- scientific article; zbMATH DE number 3314813 (Why is no real title available?)
- Learning Patterns and Pattern Sequences by Self-Organizing Nets of Threshold Elements
- Modeling Brain Function
- Neural networks and physical systems with emergent collective computational abilities
- Stimulus-Driven and Spontaneous Dynamics in Excitatory-Inhibitory Recurrent Neural Networks for Sequence Representation
This page was built for publication: Learning sequence attractors in recurrent networks with hidden neurons
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6587017)
