Loading…
NPC 2017 has ended
View analytic
Thursday, November 2 • 11:55am - 12:20pm
Advances in Neural Models for Sequence Prediction: DeepTech Summit

Sign up or log in to save this to your schedule and see who's attending!

Feedback form is now closed.

The ability to predict sequences in response to complex inputs is fundamental to many real-life tasks such as translation, conversation assistance, image captioning, speech and handwriting recognition. In this talk, we will start with the basic LSTM-based encoder-decoder model, discuss its limitations, and examine the recent research efforts to tackle them.  One line of research attempts to fix the maximum likelihood based training objective so as to align better with inference errors.  A second line of research attempt to increase model capacity via techniques like attention, structured attention, and memory models.  I will conclude with a discussion of future research direction.


Speakers
avatar for Sunita Sarawagi

Sunita Sarawagi

Professor, IIT Bombay
Sunita Sarawagi researches in the fields of databases, data mining, and machine learning.  Her current research interests are deep learning, graphical models and information extraction.  She is institute chair professor at IIT Bombay. She got her PhD in databases from the University of California at Berkeley and a bachelors degree from IIT... Read More →


Thursday November 2, 2017 11:55am - 12:20pm
Aura 3 Vivanta by Taj, Yeshwantpur, Bengaluru, India