Title :
A combinational digital logic approach to STDP
Author :
Cassidy, Andrew ; Andreou, Andreas G. ; Georgiou, Julius
Author_Institution :
Dept. of Electr. & Comput. Eng., Johns Hopkins Univ., Baltimore, MD, USA
Abstract :
Spike Timing Dependant Plasticity (STDP) is a biologically-based Hebbian reinforcement learning rule for the unsupervised training of synaptic weights in spiking neural networks. We present a low complexity synthetic implementation of STDP using basic combinational digital logic gates. This approach attains comparable results to more complex implementations while utilizing only a fraction of the area. We use our STDP approach to replicate the experimental results of a balanced excitation experiment.
Keywords :
Hebbian learning; combinational circuits; logic gates; neural nets; unsupervised learning; Hebbian reinforcement learning rule; STDP; balanced excitation; combinational digital logic gates; spike timing dependant plasticity; spiking neural networks; synaptic weights; unsupervised training; Complexity theory; Convolution; Encoding; Neurons; Shift registers; Table lookup; Timing;
Conference_Titel :
Circuits and Systems (ISCAS), 2011 IEEE International Symposium on
Conference_Location :
Rio de Janeiro
Print_ISBN :
978-1-4244-9473-6
Electronic_ISBN :
0271-4302
DOI :
10.1109/ISCAS.2011.5937655
