A model of artificial Neural network. It consists of liquid filters and readouts. A liquid filter is a neural circuit that receives the input and produce 'liquid states', which is subsequently converted to an output by readout filters. It is naturally suitable to process real-time inputs.
References #
- Liquid state machines: motivation, theory, and applications by Wolfgang Maass
- W. Maass, T. Natschlaeger, and H. Markram, Real-time computing without stable states: a new framework for neural computation based on perturbations, Neural Computation, 14(11), 2531-2560 (2002). pdf - the first paper
- Structured liquids in liquid state machines - A master thesis on LSM.
Incoming Links #
Related Articles (Article 0) #
Suggested Pages #
- 0.585 Neuron
- 0.073 Gradient descent
- 0.029 Paper/Srivastava2014
- 0.025 Neural Turing machine
- 0.025 Ilya Sutskever
- 0.024 Jack Terwilliger
- 0.013 Paper/Graves2014NTM
- 0.013 Google
- 0.012 Long short-term memory
- 0.012 Attention (Deep learning)
- More suggestions...