Out of all the episodes in the excellent seventh season of Black Mirror, it's Plaything that sticks out to me and I suspect to anyone else who played video games in the 1990s. It's the story of socially awkward freelance games journalist, Cameron Walker, who steals the code to a new virtual pet sim named Thronglets from the developer he's meant to be interviewing. When he gets the game home, he realises the cute, intelligent little critters he's caring for on the screen have a darker ambition than simply to perform for his amusement – cue nightmarish exploration of AI and our complicity in its rise. The episode is interesting to me because … well, I was a socially awkward games journalist in the mid-1990s. But more importantly, so was Charlie Brooker.

The drone scandal surrounding the Canadian women's soccer team could have bigger implications than just this year's Games in Paris. Head coach Bev Priestman was removed from her position on Thursday night after two staff members were sent home from Paris after an investigation found that analyst Joseph Lombardi had used a drone to spy on New Zealand's practice sessions. Head coach Beverly Priestman reacts during the Women's Gold Medal match between Canada and Sweden on day 14 of the Tokyo 2020 Olympic Games at International Stadium Yokohama on Aug. 6, 2021 in Yokohama, Kanagawa, Japan. "Over the past 24 hours, additional information has come to our attention regarding previous drone use against opponents, predating the Paris 2024 Olympic Games," Canada Soccer CEO Kevin Blue said in a statement. "In light of these new revelations, Canada Soccer has made the decision to suspend Women's National Soccer Team Head Coach, Bev Priestman for the remainder of the Paris 2024 Olympic Games, and until the completion of our recently announced independent external review."

The Food and Drug Administration has approved the first artificial intelligence software that can decide, without a clinician's involvement, whether a patient might have a certain disease, the agency announced Wednesday. The software, called IDx-DR, looks for diabetic retinopathy, an eye disease that afflicts individuals with diabetes. With minimal training, health care providers can use a special camera to take a picture of the back of the patient's retina, which an algorithm then analyzes to look for the disease. If the software finds evidence of the disease, it recommends that a patient see an eye specialist. A computer program that can analyze medical images could save time and money, cutting down on unnecessary, expensive trips to specialists.

Automatically searching for optimal hyperparameter configurations is of crucial importance for applying deep learning algorithms in practice. Recently, Bayesian optimization has been proposed for optimizing hyperparameters of various machine learning algorithms. Those methods adopt probabilistic surrogate models like Gaussian processes to approximate and minimize the validation error function of hyperparameter values. However, probabilistic surrogates require accurate estimates of sufficient statistics (e.g., covariance) of the error distribution and thus need many function evaluations with a sizeable number of hyperparameters. This makes them inefficient for optimizing hyperparameters of deep learning algorithms, which are highly expensive to evaluate. In this work, we propose a new deterministic and efficient hyperparameter optimization method that employs radial basis functions as error surrogates. The proposed mixed integer algorithm, called HORD, searches the surrogate for the most promising hyperparameter values through dynamic coordinate search and requires many fewer function evaluations. HORD does well in low dimensions but it is exceptionally better in higher dimensions. Extensive evaluations on MNIST and CIFAR-10 for four deep neural networks demonstrate HORD significantly outperforms the well-established Bayesian optimization methods such as GP, SMAC, and TPE. For instance, on average, HORD is more than 6 times faster than GP-EI in obtaining the best configuration of 19 hyperparameters.

Automatically searching for optimal hyperparameter configurations is of crucial importance for applying deep learning algorithms in practice. Recently, Bayesian optimization has been proposed for optimizing hyperparameters of various machine learning algorithms. Those methods adopt probabilistic surrogate models like Gaussian processes to approximate and minimize the validation error function of hyperparameter values. However, probabilistic surrogates require accurate estimates of sufficient statistics (e.g., covariance) of the error distribution and thus need many function evaluations with a sizeable number of hyperparameters. This makes them inefficient for optimizing hyperparameters of deep learning algorithms, which are highly expensive to evaluate. In this work, we propose a new deterministic and efficient hyperparameter optimization method that employs radial basis functions as error surrogates. The proposed mixed integer algorithm, called HORD, searches the surrogate for the most promising hyperparameter values through dynamic coordinate search and requires many fewer function evaluations. HORD does well in low dimensions but it is exceptionally better in higher dimensions. Extensive evaluations on MNIST and CIFAR-10 for four deep neural networks demonstrate HORD significantly outperforms the well-established Bayesian optimization methods such as GP, SMAC, and TPE. For instance, on average, HORD is more than 6 times faster than GP-EI in obtaining the best configuration of 19 hyperparameters.

Your next Adidas runners might be made in America – by a robot. The shoemaker revealed more details today about its coming'Speedfactory,' which it previously announced would be coming to the U.S. in 2017. The factory will call Atlanta home, and feature 74,000 square feet of robot shoemaking capability, with full operational status target for the end of next year. The factory has an output capacity of 50,000 Paris of shoes per year, which is only a small slice of its overall annual shoe shipments. But the Atlanta facility will be Adidas' second Speedfactory, joining the original in its home territory of Germany.