Multi-Timescale Memory Dynamics Extend Task Repertoire in a Reinforcement Learning Network With Attention-Gated Memory.
Marco MartinolliWulfram GerstnerAditya GilraPublished in: Frontiers Comput. Neurosci. (2018)
Keyphrases
- reinforcement learning
- memory space
- memory requirements
- memory usage
- dynamic model
- network model
- computational power
- neural network
- computing power
- state space
- intrusion detection
- state information
- limited memory
- dynamically created
- data flow
- function approximation
- associative memory
- network traffic
- artificial neural networks