Data cleansing is a well studied strategy for cleaning erroneous labels in datasets, which has not yet been widely adopted in Music Information Retrieval. Previously proposed data cleansing models do not consider structured (e.g. time varying) labels, such as those common to music data. We propose a novel data cleansing model for time-varying, structured labels which exploits the local structure of the labels, and demonstrate its usefulness for vocal note event annotations in music. %Our model is trained in a contrastive learning manner by automatically creating local deformations of likely correct labels. Our model is trained in a contrastive learning manner by automatically contrasting likely correct labels pairs against local deformations of them. We demonstrate that the accuracy of a transcription model improves greatly when trained using our proposed strategy compared with the accuracy when trained using the original dataset. Additionally we use our model to estimate the annotation error rates in the DALI dataset, and highlight other potential uses for this type of model.

Deep neural networks are becoming more and more popular due to their revolutionary success in diverse areas, such as computer vision, natural language processing, and speech recognition. However, the decision-making processes of these models are generally not interpretable to users. In various domains, such as healthcare, finance, or law, it is critical to know the reasons behind a decision made by an artificial intelligence system. Therefore, several directions for explaining neural models have recently been explored. In this thesis, I investigate two major directions for explaining deep neural networks. The first direction consists of feature-based post-hoc explanatory methods, that is, methods that aim to explain an already trained and fixed model (post-hoc), and that provide explanations in terms of input features, such as tokens for text and superpixels for images (feature-based). The second direction consists of self-explanatory neural models that generate natural language explanations, that is, models that have a built-in module that generates explanations for the predictions of the model.

Ambiguity is inherent to open-domain question answering; especially when exploring new topics, it can be difficult to ask questions that have a single, unambiguous answer. In this paper, we introduce AmbigQA, a new open-domain question answering task which involves finding every plausible answer, and then rewriting the question for each one to resolve the ambiguity. To study this task, we construct AmbigNQ, a dataset covering 14,042 questions from NQ-open, an existing open-domain QA benchmark. We find that over half of the questions in NQ-open are ambiguous, with diverse sources of ambiguity such as event and entity references. We also present strong baseline models for AmbigQA which we show benefit from weakly supervised learning that incorporates NQ-open, strongly suggesting our new task and data will support significant future research effort. Our data and baselines are available at https://nlp.cs.washington.edu/ambigqa.

Over the past 60 years, AI and machine learning have made a breathtaking jump from science fiction to the real world. Though these technologies are still in their youth with greater ambitions to satisfy, they have already transformed our lives drastically. The word AI is highly misused and overused, making us think that everything from a taxi app to a toothbrush is powered by it. In reality, the technology that stands behind these inventions is changing the world right here and now. It speeds up diagnosis in hospitals, makes cars move without drivers, generates music, and writes for the novelists (it is giving me Heebie-Jeebies).

If you watch Netflix, listen to music via Spotify, or have bought a product via Amazon, you will have interacted with machine learning or AI at some level. Much of what you watch, listen to or buy comes from recommendations made by AI algorithms. More and more, algorithms are helping us to make both subtle and important life altering decisions. So, what does this mean for marketers? They are an AI-first company.

The Artificial Intelligence-as-a-Service (AIaaS) market report provides key market segments along with sub-segments, market dynamics, and key …

Like many other Fintechs, Harvest will be using artificial intelligence (AI) and machine learning (ML) algorithms to offer clients a dynamic view of their …

"Artificial intelligence, which is essentially a computer programmed in a certain way," explains Skillion Tech CEO and Founder, Pete Cooper, "it takes …

The best way to understand a machine learning algorithm is to understand how machine learning and its algorithms work.

Global Machine Learning in Communication Market analysis forecast to 2025 is a specialized and in-depth study of the industry with a focus on the …