论文信息 - A neural network for temporal sequential information

A neural network for temporal sequential information

We report a neural network model that is capable of learning arbitrary input sequences quickly and online. It is also capable of completing a sequence upon cueing from any point in the sequence and in the presence of background noise. The architecture of the neural network utilizes sigmoid-pulse generating spiking neurons together with a Hebbian learning rule with synaptic noise.

Luc Berthouze | Adriaan G. Tijsseling | L. Berthouze

[1] Luc Berthouze,et al. An episodic memory model using spiking neurons , 2000, Smc 2000 conference proceedings. 2000 ieee international conference on systems, man and cybernetics. 'cybernetics evolving to systems, humans, organizations, and their complex interactions' (cat. no.0.

[2] B. McNaughton,et al. Perception, memory, and emotion : frontiers in neuroscience , 1996 .

[3] Stevan Harnad,et al. Categories as Attractors , 1998 .

[4] D. Ferster,et al. The contribution of noise to contrast invariance of orientation tuning in cat visual cortex. , 2000, Science.

[5] Jack D. Cowan,et al. Traveling activity waves , 1998 .

[6] Tijsseling Ag,et al. Connectionist models of catergorization : a dynamical approach to cognition. , 1998 .

[7] Isaac Meilijson,et al. Effective Neuronal Learning with Ineffective Hebbian Learning Rules , 2001, Neural Computation.

[8] J. White,et al. Channel noise in neurons , 2000, Trends in Neurosciences.

[9] Luc Berthouze. BOOTSTRAPPING THE DEVELOPMENTAL PROCESS: THE FILTER HYPOTHESIS , 2000 .

[10] E. Gibson. Principles of Perceptual Learning and Development , 1969 .

[11] A. Zador. Impact of synaptic unreliability on the information transmitted by spiking neurons. , 1998, Journal of neurophysiology.

[12] C. Lee Giles,et al. Synaptic noise in dynamically-driven recurrent neural networks: convergence and generalization , 1994 .

[13] Carson C. Chow,et al. Stochastic resonance without tuning , 1995, Nature.