Faculty

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.

Moojan Ghafurian, Graham Postdoctoral Fellow in the Cheriton School of Computer Science, and Kerstin Dautenhahn, Canada 150 Chair in Intelligent Robotics in the Department of Electrical and Computer Engineering, have received a catalyst grant from the University of Waterloo’s Network for Aging Research to d

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.

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.

Jian Deng, Master’s candidate
David R. Cheriton School of Computer Science

This thesis presents Multi-view Labelling Object Detector (MLOD). The detector takes an RGB image and a LIDAR point cloud as input and follows the two-stage object detection framework \cite{girshick2015fast} \cite{ren2015faster}. A Region Proposal Network (RPN) generates 3D proposals in a Bird's Eye View (BEV) projection of the point cloud. The second stage projects the 3D proposal bounding boxes to the image and BEV feature maps and sends the corresponding map crops to a detection header for classification and bounding-box regression.

Mohammed Alliheedi, PhD candidate
David R. Cheriton School of Computer Science

Ontologies must provide the entities, concepts, and relations required by the domain being represented. The domain of interest in this paper is the biochemistry experimental procedure. The ontology language being used is OWL-DL. OWL-DL was adopted due to its well-balanced flexibility among expressiveness (e.g., class description, cardinality restriction, etc.), completeness, and decidability. These procedures are composed of procedure steps, which can be represented as sequences. Sequences are composed of totally ordered, partially ordered, and alternative subsequences.

Hamidreza Shahidi, Master’s candidate
David R. Cheriton School of Computer Science

A number of researchers have recently questioned the necessity of increasingly complex neural network (NN) architectures. In particular, several recent papers have shown that simpler, properly tuned models are at least competitive across several natural language processing (NLP) tasks.

Aman Jhunjhunwala, Master’s candidate
David R. Cheriton School of Computer Science

Recently, deep neural networks have been capable of solving complex control tasks in certain challenging environments. However, these deep learning policies continue to be hard to interpret, explain and verify, which limits their practical applicability. Decision Trees lend themselves well to explanation and verification tools but are not easy to train especially in an online fashion. The aim of this thesis is to explore online tree construction algorithms and demonstrate the technique and effectiveness of distilling reinforcement learning policies into a Bayesian tree structure.

People suffering from the early symptoms of Alzheimer’s disease often have difficulty remembering things that recently happened to them. As the disease takes root, a person’s reasoning and behaviour can change. Day-to-day routines — like handwashing — may become challenging for them and they begin to need more assistance from caregivers for simple tasks.

But now there is technology that can help.

Alexander Sachs, Master’s candidate
David R. Cheriton School of Computer Science

GitHub is an excellent democratic source of software. Unlike traditional work groups however, GitHub repositories are primarily anonymous and virtual. Traditional strategies for improving the productivity of a work group often include external consultation agencies that do in-person interviews. The resulting data from these interviews are then reviewed and their recommendations provided. In the online world however, where colleagues are often anonymous and geographically dispersed, it is often impossible to apply such approaches.

Faculty

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

Moojan Ghafurian, Kerstin Dautenhahn and Jesse Hoey awarded funding to develop emotionally intelligent robots to help people with dementia

Master’s Thesis Presentation: The Computational Benefits of Intrinsic Plasticity in Neural Networks

Master’s Thesis Presentation: Local and Cooperative Autonomous Vehicle Perception from Synthetic Datasets

Master’s Thesis Presentation: MLOD: A Multi-view 3D Object Detection Based on Robust Feature

PhD Seminar: Biochemistry Procedure-Oriented Ontology: A Case Study

Master’s Thesis Presentation: Neural Text Generation from Structured and Unstructured Data

Master’s Thesis Presentation: Policy Extraction via Online Q-Value Distillation

Emotionally intuitive artificial intelligence

Master’s Thesis Presentation: Predicting Repository Upkeep with Textual Personality Analysis

Waterloo.ai