Events

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.

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.

Please note: This master’s thesis presentation will be given online.

Nalin De Zoysa, Master’s candidate
David R. Cheriton School of Computer Science

GitHub is a collaborative platform that is used primarily for the development of software. In order to gain more insight into how teams work on GitHub, we wish to analyze the sentiment content available via communication on the platform.

Please note: This master’s thesis presentation will be given online.

Wei Sun, Master’s candidate
David R. Cheriton School of Computer Science

Predictive Coding is a hierarchical model of neural computation that approximates backpropagation using only local computations and local learning rules. An important aspect of Predictive Coding is the presence of feedback connections between layers. These feedback connections allow Predictive Coding networks to potentially be generative as well as discriminative. However, Predictive Coding networks trained on supervised classification tasks cannot generate accurate input samples close to the training inputs from the class vectors alone.

Please note: This master’s thesis presentation will be given online.

Daniel Tamming, Master’s candidate
David R. Cheriton School of Computer Science

Thanks to increases in computing power and the growing availability of large datasets, neural networks have achieved state of the art results in many natural language processing (NLP) and computer vision (CV) tasks. These models require a large number of training examples that are balanced between classes, but in many application areas they rely on training sets that are either small or imbalanced, or both. To address this, data augmentation has become standard practice in CV. This research is motivated by the observation that, relative to CV, data augmentation is underused and understudied in NLP.

Please note: This master’s thesis presentation will be given online.

Gaurav Sahu, Master’s candidate
David R. Cheriton School of Computer Science

Effective fusion of data from multiple modalities, such as video, speech, and text, is a challenging task due to the heterogeneous nature of multimodal data. In this work, we propose fusion techniques that aim to model context from different modalities effectively. Instead of defining a deterministic fusion operation, such as concatenation, for the network, we let the network decide how to combine given multimodal features more effectively.

Please note: This master’s thesis presentation will be given online.

Vikash Balasubramanian, Master’s candidate
David R. Cheriton School of Computer Science

Learning useful representations of data is a crucial task in machine learning with wide ranging applications. In this thesis we explore improving representations of models based on variational inference by improving the posterior.