CS Events Monthly View

Faculty Candidate Talk

Recent Advances and the Future of Recurrent Neural Networks

 

Download as iCal file

Monday, May 01, 2017, 10:30am

 

Although the recent resurgence of Recurrent Neural Networks (RNN) has achieved remarkable advances in sequence modeling, we are still missing many abilities of RNN necessary to model more challenging yet important natural phenomena. In this talk, I introduce some recent advances in this direction, focusing on two new RNN architectures: the Hierarchical Multiscale Recurrent Neural Networks (HM-RNN) and the Neural Knowledge Language Model (NKLM). In the HM-RNN, each layer in a multi-layered RNN learns different time-scales, adaptively to the inputs from the lower layer. The NKLM deals with the problem of incorporating factual knowledge provided by a knowledge graph into RNNs. I argue the advantages of these models and conclude the talk with a discussion on the key challenges that lie ahead.

Speaker: Sungjin Ahn

Bio

Sungjin Ahn is currently a postdoctoral researcher at the University of Montreal, working with Prof. Yoshua Bengio on Deep Learning and its applications. He received his Ph.D. in Computer Science at the University of California, Irvine, under the supervis

Location : CoRE A 301

Committee

Dimitris Metaxas and Vladimir Pavlovic

Event Type: Faculty Candidate Talk

Organization

University of Montreal