S14 (2022-2023)

Encoder-Decoder Architectures for Clinically Relevant Coronary Artery Segmentation: Applications in Stenosis Detection

Coronary X-ray angiography is a crucial clinical procedure for the diagnosis and treatment of coronary artery disease, which accounts for roughly 16% of global deaths every year. However, the images acquired in these procedures have low resolution and poor contrast, … Read More

Towards End-to-end Speech-to-text Abstractive Summarization

Speech-to-text summarization is a time-saving technique used to filter and keep pace with the daily influx of broadcast news uploaded online. The emergence of powerful deep learning-based language models, boasting impressive text generation capabilities, has directed research attention towards summarization … Read More

Artificial Intelligence in Chest Radiography: Growing pains and Interpretability

Chest radiography is one of the most ubiquitous medical imaging modalities. Nevertheless, the interpretation of chest radiography images is time-consuming and complex meaning that the field is ripe for a takeover from artificial intelligence systems. The high image throughput has … Read More

Causal DiConStruct

Model interpretability plays a central role in human-AI decision-making systems. Ideally, explanations should be expressed through semantic concepts and their causal relations in an interpretable way for the human experts. Additionally, explanation methods should be efficient, and not compromise the … Read More

Scaling Laws for Multilingual Neural Machine Translation

In this talk, we provide a large-scale empirical study of the scaling properties of multilingual neural machine translation models. We examine how increases in the model size affect the model performance and investigate the role of the training mixture composition … Read More

Artificial evolution in the natural world

Evolutionary algorithms (EA) have proved as a robust optimisation meta-heuristic in engineering problems.  When we tackle problems in multi-agent systems, the nonlinear interactions set up an increasingly challenging context.  And if the multi-agents are groups of animals interacting with artificial … Read More

Model-Value Self-Consistent Updates and Applications

Learned models of the environment provide reinforcement learning agents with flexible ways of making predictions about the environment. Models enable planning, i.e. using more computation to improve value functions or policies, without requiring additional environment interactions. In this talk, we … Read More

FairGBM: Gradient Boosting with Fairness Constraints

Tabular data is prevalent in many high-stakes domains, from financial services to public policy. In these settings, Gradient Boosted Machines (GBM) are still the state-of-the-art. However, existing in-training fairness interventions are either incompatible with GBMs, or incur significant performance losses … Read More

Dense Template Retrieval for Customer Support

Templated answers are used extensively in customer support scenarios, providing an efficient way to cover a plethora of topics, with an easily maintainable collection of templates. However, the number of templates is often too high for an agent to manually … Read More