Conventional Time Series Classification (TSC) methods are often black boxes that obscure inherent interpretation of their decision-making processes. In this work, we leverage Multiple Instance Learning (MIL) to overcome this issue, and propose a new framework called MILLET: Multiple Instance Learning for Locally Explainable Time series classification. We apply MILLET to existing deep learning TSC models and show how they become inherently interpretable without compromising (and in some cases, even improving) predictive performance. We evaluate MILLET on 85 UCR TSC datasets and also present a novel synthetic dataset that is specially designed to facilitate interpretability evaluation. On these datasets, we show MILLET produces sparse explanations quickly that are of higher quality than other well-known interpretability methods. Figure 1: Conventional TSC techniques (left) usually only provide class-level predictive probabilities. In addition, our proposed method (MILLET, right) also ...

For practical purposes, the M1 Ultra acts like a single, impossibly large slice of silicon that does it all. Apple's most powerful chip to date has 114 billion transistors packed into over a hundred processing cores dedicated to logic, graphics, and artificial intelligence, all of it connected to 128 gigabytes of shared memory. But the M1 Ultra is in fact a Frankenstein's monster, consisting of two identical M1 Max chips bolted together using a silicon interface that serves as a bridge. This clever design makes it seem as if the conjoined chips are in fact just one larger whole. As it becomes more difficult to shrink transistors in size, and impractical to make individual chips much bigger, chipmakers are beginning to stitch components together to boost processing power.

Agriculture Engineering and Technology interventions assisted farmers in ushering in the Green Revolution, which helped the country sail toward Food Security and become a net food surplus nation. Science advancements have continued to assist farmers in meeting challenges. With the advancement of Information Technology, Mobile Phones, GIS, Robotics, and now Artificial Intelligence, Agronomists and Scientists are becoming increasingly interested in addressing agricultural issues. With a huge amount of information supported by AI, on weather, prices of inputs, and Agri produce, farmers can plan field & soil preparation, place orders for the purchase of seeds and inputs, pick time window for crop sowing, harvesting, plan storage doe staggered supply of products in markets to benefit from market price discovery. The AI provides market insights that guide farmers' decisions, for example, consumers searching for millets will be interpreted as increasing demand for millets and farmers can take a cue to sow millets to reap profits instead of any other cereal or grain.

Hyderabad, India: Millets have sometimes been hailed as the next quinoa but researchers collating a global database of millet products have found this ancient grain to be orchestrating a silent food revolution that could see quinoa outstripped. The "Millet Finder", launched today, discovered a surge in the use of millets, with over a thousand modern convenient products in a very wide range, across all the inhabited continents. Launched today at FoodTec Expo by the International Crops Research Institute of the Semi-Arid Tropics (ICRISAT) and the ICAR-Indian Institute of Millets Research (IIMR), the "Millet Finder" will help users find over 500 products across 30 countries. Another 500 products are identified and set to be included and mapped by end of the year by the Smart Food team at ICRISAT, who created the database and will continue growing it. "Unless there is a consumer driven demand and movement to diversify diets, farms cannot diversify and agriculture cannot be sustainable. By diversifying staples, we can have a major impact on diets, farms and the environment. ICRISAT strongly believes in creating awareness and helping consumers make informed choices while keeping their health and the environment in view. In that respect, millets check every box," said Dr Jacqueline d'Arros Hughes, Director General, ICRISAT, and Chair, Smart Food Executive Council.

A few years ago--the company won't say exactly when--some engineers at Apple began to think the iPhone's camera could be made smarter using newly powerful machine learning algorithms known as neural networks. Before long, they were talking with a lean vice president named Tim Millet. Millet leads a team of chip architects, who got to work. When the iPhone X was unveiled last fall, Apple's camera team had added a slick new portrait mode that can digitally adjust the lighting on subjects' faces, and artfully blur the background. It took advantage of a new module added to the iPhone's main chip called the neural engine, customized to run machine learning code.