Pair-associate Learning with Modulated Spike-Time Dependent Plasticity
Yusoff, N, Grüning, A and Notley, S (2012) Pair-associate Learning with Modulated Spike-Time Dependent Plasticity In: 22nd International Conference on Artificial Neural Networks, 2012-09-11 - 2012-09-14, Lausanne, Switzerland.
Available under License : See the attached licence file.
We propose an associative learning model using reward mod- ulated spike-time dependent plasticity in reinforcement learning paradigm. The task of learning is to associate a stimulus pair, known as the predictor− choice pair, to a target response. In our model, a generic architecture of neural network has been used, with minimal assumption about the network dynamics. We demonstrate that stimulus-stimulus-response as- sociation can be implemented in a stochastic way within a noisy setting. The network has rich dynamics resulting from its recurrent connectiv- ity and background activity. The algorithm can learn temporal sequence detection and solve temporal XOR problem.
|Item Type:||Conference or Workshop Item (Conference Paper)|
|Divisions :||Faculty of Engineering and Physical Sciences > Computing Science|
|Identification Number :||https://doi.org/10.1007/978-3-642-33269-2_18|
|Additional Information :||The original publication is available at http://www.springerlink.com|
|Depositing User :||Symplectic Elements|
|Date Deposited :||25 Feb 2014 14:43|
|Last Modified :||01 Apr 2015 13:35|
Actions (login required)
Downloads per month over past year