Colin Vandenhof, Master’s candidate
David R. Cheriton School of Computer Science
Reinforcement learning (RL) is a powerful tool for developing intelligent agents, and the use of neural networks makes RL techniques more scalable to challenging real-world applications, from task-oriented dialogue systems to autonomous driving. However, one of the major bottlenecks to the adoption of RL is efficiency, as it often takes many time steps to learn an acceptable policy.
Taylor Denouden, Master’s candidate
David R. Cheriton School of Computer Science
Recently, much research has been published for detecting when a classification neural network is presented with data that does not fit into one of the class labels the network learned at train time. These so-called out-of-distribution (OOD) detection techniques hold promise for improving safety in systems where unusual or novel inputs may result in errors that endanger human lives.
Sachin Vernekar, Master’s candidate
David R. Cheriton School of Computer Science
Discriminatively trained neural classifiers can be trusted only when the input data comes from the training distribution (in-distribution). Therefore, detecting out-of-distribution (OOD) samples is very important to avoid classification errors.
Wei Tao Chen, Master’s candidate
David R. Cheriton School of Computer Science
Image semantic segmentation is an important problem in computer vision. However, training a deep neural network for semantic segmentation in supervised learning requires expensive manual labeling. Active learning (AL) addresses this problem by automatically selecting a subset of the dataset to label and iteratively improve the model. This minimizes labeling costs while maximizing performance. Yet, deep active learning for image segmentation has not been systematically studied in the literature.
Aravind Balakrishnan, Master’s candidate
David R. Cheriton School of Computer Science
The behaviour planning subsystem, which is responsible for high-level decision making and planning, is an important aspect of an autonomous driving system. There are advantages to using a learned behaviour planning system instead of traditional rule-based approaches. However, high quality labelled data for training behaviour planning models is hard to acquire. Thus, reinforcement learning (RL), which can learn a policy from simulations, is a viable option for this problem.
Ashish Gaurav, Master’s candidate
David R. Cheriton School of Computer Science
Continual learning is often confounded by “catastrophic forgetting” that prevents neural networks from learning tasks sequentially. In the case of real world classification systems that are safety-validated prior to deployment, it is essential to ensure that validated knowledge is retained.
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.
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.
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.