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:

Braden Hurl, Master’s candidate
David R. Cheriton School of Computer Science

This work introduces the Precise Synthetic Image and LiDAR (PreSIL) dataset for autonomous vehicle perception. Grand Theft Auto V (GTA V), a commercial video game, has a large, detailed world with realistic graphics, which provides a diverse data collection environment. Existing works creating synthetic LiDAR data for autonomous driving with GTA V have not released their datasets, rely on an in-game raycasting function which represents people as cylinders, and can fail to capture vehicles past 30 metres.

Nolan Shaw, Master’s candidate
David R. Cheriton School of Computer Science

In this work, I study the relationship between a local, intrinsic update mechanism and a synaptic, error-based learning mechansim in ANNs. I present a local intrinsic rule that I developed, dubbed IP, that was inspired by the Infomax rule. Like Infomax, this IP rule works by controlling the gain and bias of a neuron to regulate its rate of fire. I discuss the biological plausibility of this rule and compare it to batch normalisation.

Friday, September 27, 2019 4:00 pm - 4:00 pm EDT (GMT -04:00)

Seminar: Learning Neural Networks with Adaptive Regularization

Han Zhao, PhD candidate
Carnegie Mellon University

Feed-forward neural networks can be understood as a combination of an intermediate representation and a linear hypothesis. While most previous works aim to diversify the representations, we explore the complementary direction by performing an adaptive and data-dependent regularization motivated by the empirical Bayes method.

Monday, October 21, 2019 12:00 pm - 12:00 pm EDT (GMT -04:00)

Seminar: Active Inference Across Scales: From the Brain to the Body and Culture

Maxwell Ramstead, McGill University

The active inference framework explains a deeply puzzling characteristic of living systems, that they resist the natural tendency towards dissipation; namely, the entropic decay that is dictated by the second law of thermodynamics. Living systems manage to maintain themselves in a limited number of states, i.e., their phenotypical states. How do organisms accomplish this incredible feat? What does it mean to be alive? How are they integrated across the scales at which they exist — from subcellular processes and neural networks, to embodied action and culture? In the active inference framework, the actions and bodies of organisms encode expectations (or Bayesian beliefs) about the world, and act to make those expectations come true. 

Friday, November 8, 2019 11:00 am - 11:00 am EST (GMT -05:00)

AI Seminar: Spiking Neural Networks for More Efficient AI Algorithms

Chris Eliasmith, Director of the Centre for Theoretical Neuroscience
Department of Systems Design Engineering

Spiking neural networks (SNNs) have received little attention from the AI community, although they compute in a fundamentally different — and more biologically inspired — manner than standard artificial neural networks (ANNs). This can be partially explained by the lack of hardware that natively supports SNNs. However, several groups have recently released neuromorphic hardware that supports SNNs. 

Wednesday, November 27, 2019 10:00 am - 10:00 am EST (GMT -05:00)

PhD Defence: Emotion-Aware and Human-Like Autonomous Agents

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

In human-computer interaction (HCI), one of the technological goals is to build human-like artificial agents that can think, decide and behave like humans during the interaction. A prime example is a dialogue system, where the agent should converse fluently and coherently with a user and connect with them emotionally. Humanness and emotion-awareness of interactive artificial agents have been shown to improve user experience and help attain application-specific goals more quickly. However, achieving human-likeness in HCI systems is contingent on addressing several philosophical and scientific challenges. In this thesis, I address two such challenges: replicating the human ability to 1) correctly perceive and adopt emotions, and 2) communicate effectively through language.

Thursday, November 28, 2019 2:00 pm - 2:00 pm EST (GMT -05:00)

AI Seminar: Fair Representation in Group Decision-making

Edith Elkind, Department of Computer Science
University of Oxford

Suppose that a group of agents want to select k > 1 alternatives from a given set, and each agent indicates which of the alternatives are acceptable to her: the alternatives could be conference submissions, applicants for a scholarship or locations for a fast food chain. In this setting it is natural to require that the set of winners represents the voters fairly, in the sense that large groups of voters with similar preferences have at least some of their approved alternatives in the winning set. 

Jaejun Lee, Master’s candidate
David R. Cheriton School of Computer Science

Used for simple voice commands and wake-word detection, keyword spotting (KWS) is the task of detecting pre-determined keywords in a stream of utterances. A common implementation of KWS involves transmitting audio samples over the network and detecting target keywords in the cloud with neural networks because on-device application development presents compatibility issues with various edge devices and provides limited supports for deep learning. Unfortunately, such an architecture can lead to unpleasant user experience because network latency is not deterministic. Furthermore, the client-server architecture raises privacy concerns because users lose control over the audio data once it leaves the edge device. 

Xin Lian, Master’s candidate
David R. Cheriton School of Computer Science

The problem of language alignment has long been an exciting topic for Natural Language Processing researchers. Current methods for learning cross-domain correspondences at the word level rely on distributed representations of words. Therefore, the recent development in the word computational linguistics and neural language modeling has led to the development of the so-called zero-shot learning paradigm.

Thursday, December 5, 2019 2:30 pm - 2:30 pm EST (GMT -05:00)

AI Seminar: Towards Fair and Accurate Peer Review

Ivan Stelmakh, PhD candidate
Machine Learning Department, School of Computer Science
Carnegie Mellon University

Peer review is the backbone of scholarly research and fairness of this process is crucial for the successful development of academia. In this talk, we will discuss our two recent works on fairness of peer review. In the first part of the talk, we will focus on the automated assignment of papers to reviewers in the conference setup. We will show that the assignment procedure currently employed by NeurIPS and ICML does not guarantee fairness and may discriminate against some submissions. In contrast, we will present the assignment algorithm that simultaneously ensures fairness and accuracy of the resulting allocation.