elf-supervised learning (SSL) has proven vital for advancing research in natural language processing (NLP) and computer vision (CV). The paradigm pretrains a shared model on large volumes of unlabeled data and achieves state-of-the-art (SOTA) for various tasks with minimal adaptation. However, the speech processing community lacks a similar setup to systematically explore the paradigm. To bridge this gap, we introduce Speech processing Universal PERformance Benchmark (SUPERB).
Read MoreTag: Paper
[Book] Advancing AI theory with a first-principles understanding of deep neural networks
Lacking theoretical understanding didn’t stop people from improving on the steam engine, of course, but discovering the principles of the heat engine led to rapid improvements. AI today is at a similar juncture.
Read MoreFacebook AI’s latest Computer Vision Model SEER teaches itself to Classify
Facebook recently unveiled an AI-driven SEER model that can analyze billions of images without any labels or captions, then detect and classify these images all by itself.
Read MoreBritish intelligence agency GCHQ publishes ‘Ethics of AI’ report
The intelligence agency’s first-ever public report details how AI can be used “ethically” for cyber operations. GCHQ (Government Communications Headquarters) is tasked with providing signals intelligence and information assurance to the government and armed forces of the United Kingdom and its allies. Jeremy Fleming, Director of GCHQ, said: “We need honest, mature conversations about the […]
Read MoreAI helps patients to get more rest while reducing staff workload
A team from Feinstein Institutes for Research thinks AI could be key to helping patients get more rest while reducing the burden on healthcare staff. Everyone knows how important adequate sleep is for recovery. However, patients in pain – or just insomniacs like me – can struggle to get the sleep they need. “Rest is…
Read MoreMicrosoft’s new AI auto-captions images for the visually impaired
A new AI from Microsoft aims to automatically caption images in documents and emails so that software for visual impairments can read it out. Researchers from Microsoft explained their machine learning model in a paper on preprint repository arXiv. The model uses VIsual VOcabulary pre-training (VIVO) which leverages large amounts of paired image-tag data to…
Read MoreSpoken Dialogue Systems – NLU, NLP, ML great papers
Useful library. Selection of papers referencing Spoken Dialogue Systems, with and without code.
Read MoreA survey of Deep Learning for scientific discovery
We have seen fundamental breakthroughs in core machine learning, driven by advances in deep neural networks. At the same time, the amount of data collected is dramatically increasing in size and complexity.
Read MoreList of inverse Reinforcement Learning (IRL) papers
Inverse Reinforcement Learning papers: A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models. (IRL, Algorithms, Apprenticeship Learning, Maximum Margin Planning, Maximum Entropy, Nonlinear with Gaussian Processes, Generative Adversarial Imitation Learning).
Read MoreAlgorithms, machine learning and other lecture notes
Algorithms, machine learning and other lecture notes. A text book by Jeff Erickson, 1st Edition, June 2019 at the University of Illinois.
Read MoreThe non-technical guide to Machine Learning & Artificial Intelligence
A non-technical guide to Machine Learning & Artificial Intelligence. ML & AI have seized mindshare in a way few topics have in recent memory. Everything from our jobs, to the wars we wage, to the food we eat, to the beer we drink, to the software we write will be affected.
Read MoreInverse Reinforcement Learning with Multiple Ranked Experts
Inverse Reinforcement Learning with Markov Decision Process models and unspecified reward functions, how performance varies with set of demonstrators to optimize learning behavior.
Read MoreWhitepaper: Artificial Intelligence & Finance
Artificial Intelligence or “AI” offers an unprecedented ability to improve the accuracy and predictability of Budgeting, Planning and Forecasting (BP&F). This is able to reduce the expensive and time intensive exercise of the annual budgeting process.
Read MoreWhitepaper: Artificial Intelligence & Brand Management
White paper focused on brand communication, promotion, crisis management using Artificial Intelligence to strategically enhance and expand management tools, as well as providing guidance in support of public crisis decisions.
Read More