Learning temporal sequences by local synaptic changes
We consider fully connected neural networks in which synaptic weights are continuously slightly updated according to the activity of their pre- and post-synaptic neurons. The synaptic weights change slowly and therefore, at any time, the network behaves as if the weights were constant. Nevertheless, over long periods, the synaptic changes accumulate to produce significant changes in the behaviour of the network. We show that simple synaptic changes may produce networks capable of complex dynamical behaviour in the presence of noise. In particular, if such a network is trained by an external stimulus that forces it to go through a fixed sequence of states, it will, after sufficient training, be capable of going through the same sequence of states on its own initiative, without any external driving. We assume that our networks have only one mode of operation, i.e. there is no distinction between the training and the retrieval mode, except for the values of the external stimulus. Therefore, synaptic modifications take place also during the retrieval of temporal sequences. The modifications brought about by the spontaneous retrieval may improve the performance of the network. The biological plausibility of the rules governing the synaptic changes is discussed.
- Temporal learning rule and dynamic neural network model
- Networks that learn the precise timing of event sequences
- Synaptic depression as an intrinsic driver of reinstatement dynamics in an attractor network
- Computational consequences of temporally asymmetric learning rules. II: Sensory image cancellation
- Spatiotemporal discrimination in attractor networks with short-term synaptic plasticity
- Synaptic organizations and dynamical properties of weakly connected neural oscillators. II: Learning phase information
- The dynamics of Learning and memory: lessons from neuroscience
- Learning a sparse code for temporal sequences using STDP and sequence compression
- Temporal association
- Perceptron-like learning in time-summating neural networks
- Modelling of the Bonhoeffer-effect during LTP learning
- scientific article; zbMATH DE number 2044706 (Why is no real title available?)
- Efficient temporal processing with biologically realistic dynamic synapses
- Computational capacity of time-recurrent networks
- Temporal Hebbian learning in rate-coded neural networks: A theoretical approach towards classical conditioning
- Temporally Asymmetric Learning Supports Sequence Processing in Multi-Winner Self-Organizing Maps
- Learning in neural networks with partially structured synaptic transitions
- A model for complex sequence learning and reproduction in neural populations
- Faithful and unfaithful students in time series learning
- Using conceptors to manage neural long-term memories for temporal patterns
- Strongly Improved Stability and Faster Convergence of Temporal Sequence Learning by Using Input Correlations Only
- Learning Only When Necessary: Better Memories of Correlated Patterns in Networks with Bounded Synapses
- A self-organizing context-based approach to the tracking of multiple robot trajectories
This page was built for publication: Learning temporal sequences by local synaptic changes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4034537)
