Events

Filter by:

Limit to events where the first date of the event:
Date range
Limit to events where the first date of the event:
Limit to events where the title matches:
Limit to events where the type is one or more of:
Limit to events tagged with one or more of:
Limit to events where the audience is one or more of:
Thursday, December 13, 2018 4:00 pm - 4:00 pm EST (GMT -05:00)

PhD Seminar: Beyond LIF: The Computational Power of Passive Dendritic Trees

Andreas Stöckel, PhD candidate
David R. Cheriton School of Computer Science

The artificial neurons typically employed in machine learning and computational neuroscience bear little resemblance to biological neurons. They are often derived from the “leaky integrate and fire” (LIF) model, neglect spatial extent, and assume a linear combination of input variables. It is well known that these simplifications have a profound impact on the family of functions that can be computed in a single-layer neural network. 

Friday, December 14, 2018 3:00 pm - 3:00 pm EST (GMT -05:00)

PhD Seminar: Progressive Memory Banks for Incremental Domain Adaptation

Nabiha Asghar, PhD candidate
David R. Cheriton School of Computer Science

We address the problem of incremental domain adaptation (IDA). We assume each domain comes one after another, and that we could only access data in the current domain. The goal of IDA is to build a unified model performing well on all the domains that we have encountered. We propose to augment a recurrent neural network (RNN) with a directly parameterized memory bank, which is retrieved by an attention mechanism at each step of RNN transition. The memory bank provides a natural way of IDA: when adapting our model to a new domain, we progressively add new slots to the memory bank, which increases the number of parameters, and thus the model capacity. 

Thursday, January 24, 2019 10:30 am - 10:30 am EST (GMT -05:00)

AI Seminar: Learning to Understand Entities in Text

Eunsol Choi, Paul G. Allen School of Computer Science
University of Washington

Real world entities such as people, organizations and countries play a critical role in text. Reading offers rich explicit and implicit information about these entities, such as the categories they belong to, relationships they have with other entities, and events they participate in. 

Brandon Alcox, Master’s candidate
David R. Cheriton School of Computer Science

This thesis investigates the application of various fields of artificial intelligence to the domain of sports management and analysis. The research in this thesis is primarily focused on the entry draft for the National Hockey League, though many of the models proposed may be applied to other sports and leagues with minimal adjustments. 

Adam Schunk, Master’s candidate
David R. Cheriton School of Computer Science

Over the past years online social networks have become a major target for marketing strategies, generating a need for methods to efficiently spread information through these networks. Close-knit communities have developed on these platforms through groups of users connecting with likeminded individuals. 

Tuesday, February 19, 2019 3:00 pm - 3:00 pm EST (GMT -05:00)

PhD Seminar: Modelling the Continuum of Emotions in Neural Dialogue Systems

Nabiha Asghar, PhD candidate
David R. Cheriton School of Computer Science

Most of the existing neural conversational models process natural language primarily on a lexico-syntactic level, thereby ignoring one of the most crucial components of human-to-human dialogue: its affective content. We take a step in this direction by proposing three novel ways to incorporate affective/emotional aspects into long short term memory (LSTM) encoder-decoder neural conversation models: (1) affective word embeddings, which are cognitively engineered, (2) affect-based objective functions that augment the standard cross-entropy loss, and (3) affectively diverse beam search for decoding.

Monday, February 25, 2019 10:30 am - 10:30 am EST (GMT -05:00)

AI Seminar: Interactive Learning and Decision Making with Machines and People

Yuxin Chen, Postdoctoral scholar, Department of Computing and Mathematical Sciences
California Institute of Technology

How can we intelligently acquire information for decision making, when facing a large volume of data? 

In this talk, I will focus on learning and decision making problems that arise in robotics, scientific discovery and human-centered systems, and present how we can develop principled approaches that actively extract information, identify the most relevant data for the learning tasks and make effective decisions under uncertainty.

Thursday, February 28, 2019 10:30 am - 10:30 am EST (GMT -05:00)

AI Seminar: Visual Question Answering and Beyond

Aishwarya Agrawal, PhD candidate
School of Interactive Computing, Georgia Tech

In this talk, I will present our work on a multi-modal AI task called Visual Question Answering (VQA) — given an image and a natural language question about the image (e.g., “What kind of store is this?”, “Is it safe to cross the street?”), the machine’s task is to automatically produce an accurate natural language answer (“bakery”, “yes”).

Wednesday, March 27, 2019 4:30 pm - 4:30 pm EDT (GMT -04:00)

PhD Seminar: Semi-supervised Clustering for De-duplication

Shrinu Kushagra, PhD candidate
David R. Cheriton School of Computer Science

Data de-duplication is the task of detecting multiple records that correspond to the same real-world entity in a database. In this work, we view de-duplication as a clustering problem. We introduce a framework which we call promise correlation clustering. Given a complete graph \(G\) with the edges labeled \(0\) and \(1\), the goal is to find a clustering that minimizes the number of \(0\) edges within a cluster plus the number of \(1\) edges across different clusters (or correlation loss). The optimal clustering can also be viewed as a complete graph \(G^*\) with edges corresponding to points in the same cluster being labeled \(0\) and other edges being labeled \(1\).