Skip to Main Content
 

Global Search Box

 
 
 
 

Files

ETD Abstract Container

Abstract Header

Chaos and Learning in Discrete-Time Neural Networks

Abstract Details

2015, BA, Oberlin College, Mathematics.
We study a family of discrete-time recurrent neural network models in which the synaptic connectivity changes slowly with respect to the neuronal dynamics. The fast (neuronal) dynamics of these models display a wealth of behaviors ranging from simple convergence and oscillation to chaos, and the addition of slow (synaptic) dynamics which mimic the biological mechanisms of learning and memory induces complex multiscale dynamics which render rigorous analysis quite difficult. Nevertheless, we prove a general result on the interplay of these two dynamical timescales, demarcating a regime of parameter space within which a gradual dampening of chaotic neuronal behavior is induced by a broad class of learning rules.
Jim Walsh (Advisor)
23 p.

Recommended Citations

Citations

  • Banks, J. M. (2015). Chaos and Learning in Discrete-Time Neural Networks [Undergraduate thesis, Oberlin College]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=oberlin1445945609

    APA Style (7th edition)

  • Banks, Jess. Chaos and Learning in Discrete-Time Neural Networks. 2015. Oberlin College, Undergraduate thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=oberlin1445945609.

    MLA Style (8th edition)

  • Banks, Jess. "Chaos and Learning in Discrete-Time Neural Networks." Undergraduate thesis, Oberlin College, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=oberlin1445945609

    Chicago Manual of Style (17th edition)