A Preliminary Neural Model for Movement Direction Recognition Based on Biologically Plausible Plasticity Rules

In this work we implement a neural architecture for recognizing the direction of movement using neural properties that are consistent with biological findings like intrinsic plasticity and synaptic metaplasticity. The network architecture has two memory layers and two competitive layers. This un-supervised neural network is able to identify the direction of movement of an object, being a promising network for object tracking, hand-written and speech recognition.

[1]  Javier Ropero Peláez,et al.  Plato's theory of ideas revisited , 1997, Neural Networks.

[2]  Javier Ropero Peláez,et al.  Towards a neural network based therapy for hallucinatory disorders , 2000, Neural Networks.

[3]  M.G. Simoes,et al.  Predictive maintenance oriented neural network system - PREMON , 2001, IECON'01. 27th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.37243).

[4]  Niraj S. Desai,et al.  Plasticity in the intrinsic excitability of cortical pyramidal neurons , 1999, Nature Neuroscience.

[5]  G. Shepherd.  The Synaptic Organization of the Brain , 1979 .

[6]  C. Koch,et al.  Is perception discrete or continuous? , 2003, Trends in Cognitive Sciences.

[7]  Javier Ropero Peláez,et al.  Biological Clues for Up-to-Date Artificial Neurons , 2007 .

[8]  Niraj S. Desai,et al.  Homeostatic plasticity in the CNS: synaptic and intrinsic forms , 2003, Journal of Physiology-Paris.

[9]  Marcelo Godoy Simões,et al.  A computational model of synaptic metaplasticity , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).