Credit: World Scientific
Have you ever wondered if it s possible to learn all there is to know about machine learning and deep learning from a book?
Machine Learning A Journey to Deep Learning, with Exercises and Answers is designed to give the self-taught student a solid foundation in machine learning with step-by-step solutions to the formative exercises and many concrete examples. By going through this text, readers should become able to apply and understand machine learning algorithms as well as create new ones.
The main parts of the book address linear and nonlinear regression, supervised learning, learning theory, feature extraction and unsupervised learning. The statistical approach leads to the definition of regularization out of the example of regression. Building on regression, we develop the theory of perceptrons and logistic regression. The book investigates the relation between bias and variance as a consequence of a finite training sample set that is used in machine
E-Mail
How best to evaluate the performance of a group testing strategy for the SARS-CoV-2 virus, which involves pooling samples from multiple individuals in order to conduct a single RT-PCR test on the whole group? To do precisely that, scientists from the CNRS, l université Grenoble Alpes, and l université Sorbonne Paris Nord1 have developed a model that evaluates the efficiency of such tests. Their theoretical study accounts for both dilution effect and the detection limits of the RT-PCR test, in an effort to assess the number of potential false negatives based on pooled sample size, to optimize group size thereby minimizing epidemic risk, and finally to more accurately determine the number of contaminated individuals within a given population. It was published on March 4, 2021 in
E-Mail
As millions of Fantasy Premier League players mull over a decision whether to start Bruno Fernandes or Mohamed Salah in their teams this weekend, new research by the University of Limerick in Ireland has unlocked the secrets of the popular online game.
A new study by a team of researchers at UL has identified the underlying tactics used by the top-ranked competitors among the seven million players of Fantasy Premier League (FPL), the official - and world s largest - fantasy football game of the English Premier League.
Joseph O Brien, Professor James Gleeson, and Dr David O Sullivan, based within the Mathematics Applications Consortium for Science and Industry (MACSI) in the Department of Mathematics and Statistics at UL, have just published research in
E-Mail
IMAGE: It turns out that pronghorn a speedy North American ungulate prized for its graceful gait can be bullies. view more
Credit: Tom Koerner/USFWS
Humans and animals alike constantly size up one another. In the workplace, a new employee quickly learns which coworkers are the most respected and therefore hold more power. Big brothers boss around little brothers. In nature, a dominant male chimpanzee fights off would-be intruders. Even fish and octopi interact within social hierarchies.
These pecking orders have been studied within the behavioral ecology world for almost 100 years. How individuals interact can affect access to food and mates even survival and insights into those behaviors can lead to better management of threatened and endangered populations. But few studies have explored what the animals that live within these dominance hierarchies actually know about each other. The more animals know about each other, the more they may be able to
E-Mail
IMAGE: A simulated soft robot controlled to reach the same target (red dot) while acting either soft (left) or stiff (right). view more
Credit: Courtesy of James Bern and Daniela Rus
Imagine a robot.
Perhaps you ve just conjured a machine with a rigid, metallic exterior. While robots armored with hard exoskeletons are common, they re not always ideal. Soft-bodied robots, inspired by fish or other squishy creatures, might better adapt to changing environments and work more safely with people.
Roboticists generally have to decide whether to design a hard- or soft-bodied robot for a particular task. But that tradeoff may no longer be necessary.