Wind energy is expected to be one of the leading ways to achieve the goals of the Paris Agreement but it in turn heavily depends on effective management of its operations and maintenance (O&M) costs. Blade failures account for one-third of all O&M costs thus making accurate detection of blade damages, especially cracks, very important for sustained operations and cost savings. Traditionally, damage inspection has been a completely manual process thus making it subjective, error-prone, and time-consuming. Hence in this work, we bring more objectivity, scalability, and repeatability in our damage inspection process, using deep learning, to miss fewer cracks. We build a deep learning model trained on a large dataset of blade damages, collected by our drone-based inspection, to correctly detect cracks. Our model is already in production and has processed more than a million damages with a recall of 0.96. We also focus on model interpretability using class activation maps to get a peek into the model workings. The model not only performs as good as human experts but also better in certain tricky cases. Thus, in this work, we aim to increase wind energy adoption by decreasing one of its major hurdles - the O\&M costs resulting from missing blade failures like cracks.

Transformer-based language models have recently achieved remarkable results in many natural language tasks. However, performance on leaderboards is generally achieved by leveraging massive amounts of training data, and rarely by encoding explicit linguistic knowledge into neural models. This has led many to question the relevance of linguistics for modern natural language processing. In this dissertation, I present several case studies to illustrate how theoretical linguistics and neural language models are still relevant to each other. First, language models are useful to linguists by providing an objective tool to measure semantic distance, which is difficult to do using traditional methods. On the other hand, linguistic theory contributes to language modelling research by providing frameworks and sources of data to probe our language models for specific aspects of language understanding. This thesis contributes three studies that explore different aspects of the syntax-semantics interface in language models. In the first part of my thesis, I apply language models to the problem of word class flexibility. Using mBERT as a source of semantic distance measurements, I present evidence in favour of analyzing word class flexibility as a directional process. In the second part of my thesis, I propose a method to measure surprisal at intermediate layers of language models. My experiments show that sentences containing morphosyntactic anomalies trigger surprisals earlier in language models than semantic and commonsense anomalies. Finally, in the third part of my thesis, I adapt several psycholinguistic studies to show that language models contain knowledge of argument structure constructions. In summary, my thesis develops new connections between natural language processing, linguistic theory, and psycholinguistics to provide fresh perspectives for the interpretation of language models.

The increasing penetration of distributed energy resources in low-voltage networks is turning end-users from consumers to prosumers. However, the incomplete smart meter rollout and paucity of smart meter data due to the regulatory separation between retail and network service provision make active distribution network management difficult. Furthermore, distribution network operators oftentimes do not have access to real-time smart meter data, which creates an additional challenge. For the lack of better solutions, they use blanket rooftop solar export limits, leading to suboptimal outcomes. To address this, we designed a conditional generative adversarial network (CGAN)-based model to forecast household solar generation and electricity demand, which serves as an input to chance-constrained optimal power flow used to compute fair operating envelopes under uncertainty.

The COVID-19 pandemic has brought forth the importance of epidemic forecasting for decision makers in multiple domains, ranging from public health to the economy as a whole. While forecasting epidemic progression is frequently conceptualized as being analogous to weather forecasting, however it has some key differences and remains a non-trivial task. The spread of diseases is subject to multiple confounding factors spanning human behavior, pathogen dynamics, weather and environmental conditions. Research interest has been fueled by the increased availability of rich data sources capturing previously unobservable facets and also due to initiatives from government public health and funding agencies. This has resulted, in particular, in a spate of work on 'data-centered' solutions which have shown potential in enhancing our forecasting capabilities by leveraging non-traditional data sources as well as recent innovations in AI and machine learning. This survey delves into various data-driven methodological and practical advancements and introduces a conceptual framework to navigate through them. First, we enumerate the large number of epidemiological datasets and novel data streams that are relevant to epidemic forecasting, capturing various factors like symptomatic online surveys, retail and commerce, mobility, genomics data and more. Next, we discuss methods and modeling paradigms focusing on the recent data-driven statistical and deep-learning based methods as well as on the novel class of hybrid models that combine domain knowledge of mechanistic models with the effectiveness and flexibility of statistical approaches. We also discuss experiences and challenges that arise in real-world deployment of these forecasting systems including decision-making informed by forecasts. Finally, we highlight some challenges and open problems found across the forecasting pipeline.

In many areas, we have well-founded insights about causal structure that would be useful to bring into our trained models while still allowing them to learn in a data-driven fashion. To achieve this, we present the new method of interchange intervention training (IIT). In IIT, we (1) align variables in a causal model (e.g., a deterministic program or Bayesian network) with representations in a neural model and (2) train the neural model to match the counterfactual behavior of the causal model on a base input when aligned representations in both models are set to be the value they would be for a source input. IIT is fully differentiable, flexibly combines with other objectives, and guarantees that the target causal model is a causal abstraction of the neural model when its loss is zero. We evaluate IIT on a structural vision task (MNIST-PVR), a navigational language task (ReaSCAN), and a natural language inference task (MQNLI). We compare IIT against multi-task training objectives and data augmentation. In all our experiments, IIT achieves the best results and produces neural models that are more interpretable in the sense that they more successfully realize the target causal model.

Crises such as natural disasters, global pandemics, and social unrest continuously threaten our world and emotionally affect millions of people worldwide in distinct ways. Understanding emotions that people express during large-scale crises helps inform policy makers and first responders about the emotional states of the population as well as provide emotional support to those who need such support. We present CovidEmo, ~3K English tweets labeled with emotions and temporally distributed across 18 months. Our analyses reveal the emotional toll caused by COVID-19, and changes of the social narrative and associated emotions over time. Motivated by the time-sensitive nature of crises and the cost of large-scale annotation efforts, we examine how well large pre-trained language models generalize across domains and timeline in the task of perceived emotion prediction in the context of COVID-19. Our analyses suggest that cross-domain information transfers occur, yet there are still significant gaps. We propose semi-supervised learning as a way to bridge this gap, obtaining significantly better performance using unlabeled data from the target domain.

A 48-year-old patient in New York City who is unable to move and speak due to severe paralysis from ALS became the first to receive a permanent brain implant that could allow him to communicate telepathically - a milestone for Synchron, the startup behind the technology, which beat Elon Musk's Neuralink to the punch with its advance. The procedure took place July 6 at Mount Sinai West medical center in Manhattan, where a 1.5-inch long implant - a brain-computer interface (BCI) as a stentrode - made of wires and electrodes was implanted into the patient's brain without the need for cutting into their skull or damaging tissue. 'The first-in-human implant of an endovascular BCI in the U.S. is a major clinical milestone that opens up new possibilities for patients with paralysis,' said Dr. Tom Oxley, CEO & Founder of Synchron, in a statement. 'The first-in-human implant of an endovascular BCI in the U.S. is a major clinical milestone that opens up new possibilities for patients with paralysis,' said Dr. Tom Oxley, CEO & Founder of Synchron, in a statement. 'Our technology is for the millions of people who have lost the ability to use their hands to control digital devices.

Fraud is evolving, and many Australian businesses may struggle to keep up with fraudsters who are continuing to find new ways to evade detection and exploit vulnerabilities. In the twelve months to June 2021 alone, the Australian Payments Network found fraud on payment card transactions totalled $490.1 million, an increase of 9.2 per cent from the year before. Further, research from Statista shows that as of 2021, around 1.25 million dollars had been lost in online shopping scams in Australia. For retailers of all sizes, it has never been more important to get ahead and proactively find a solution that helps to stop fraudulent transactions without turning away legitimate customers and limiting opportunities for growth. What your business needs, however, depends on the size of your organisation or the trajectory of growth that you are on.

Renewable resources like sunlight provide a sustainable and carbon neutral mechanism to generate power. Governments in many countries are providing incentives and subsidies to households to install solar panels as part of small-scale renewable energy schemes. This has created a huge demand for solar panels. Reaching out to potential customers at the right time, through the right channel, and with attractive offers is very crucial for solar and energy companies. They're looking for cost-efficient approaches and tools to conduct targeted marketing to proactively reach out to potential customers.

We present the Caltech Fish Counting Dataset (CFC), a large-scale dataset for detecting, tracking, and counting fish in sonar videos. We identify sonar videos as a rich source of data for advancing low signal-to-noise computer vision applications and tackling domain generalization in multiple-object tracking (MOT) and counting. In comparison to existing MOT and counting datasets, which are largely restricted to videos of people and vehicles in cities, CFC is sourced from a natural-world domain where targets are not easily resolvable and appearance features cannot be easily leveraged for target re-identification. With over half a million annotations in over 1,500 videos sourced from seven different sonar cameras, CFC allows researchers to train MOT and counting algorithms and evaluate generalization performance at unseen test locations. We perform extensive baseline experiments and identify key challenges and opportunities for advancing the state of the art in generalization in MOT and counting.