"Dynamic Boltzmann machines", Takayuki Osogami
Neural Computation Unit (Doya Unit) would like to invite you to a seminar as follows.
Date: Monday, March 28, 2016
Venue: Seminar Room C209 - Center Bldg
Speaker: Dr. Takayuki Osogami
IBM Academy of Technology, IBM Research - Tokyo
Title: Dynamic Boltzmann machines
Abstract: An artificial neural network, such as a Boltzmann machine, can be trained with the Hebb rule so that it stores static patterns and retrieves a particular pattern when an associated cue is presented to it. Such a network, however, cannot effectively deal with dynamic patterns in the manner of living creatures. Here, we design a dynamic Boltzmann machine (DyBM) and a learning rule that has some of the properties of spike-timing dependent plasticity (STDP), which has been postulated for biological neural networks. We train a DyBM consisting of only seven neurons in a way that it memorizes the sequence of the bitmap patterns in an alphabetical image "SCIENCE" and its reverse sequence and retrieves either sequence when a partial sequence is presented as a cue. The DyBM is to STDP as the Boltzmann machine is to the Hebb rule. This research is supported by CREST, JST, and the talk is based on a paper appeared in http://www.nature.com/articles/srep14149.
We hope to see many of you.
Neural Computation Unit