Changepoint detection identifies significant shifts in data sequences, making it important in areas like finance, genetics, and healthcare. The Optimal Partitioning algorithms efficiently detect these changes, using a penalty parameter to limit the changepoints count. Determining the optimal value for this penalty can be challenging. Traditionally, this process involved manually extracting statistical features, such as sequence length or variance to make the prediction. This study proposes a novel approach that uses recurrent networks to learn this penalty directly from raw sequences by automatically extracting features. Experiments conducted on 20 benchmark genomic datasets show that this novel method generally outperforms traditional ones in changepoint detection accuracy.

Receiver Operating Characteristic (ROC) curves are useful for evaluation in binary classification and changepoint detection, but difficult to use for learning since the Area Under the Curve (AUC) is piecewise constant (gradient zero almost everywhere). Recently the Area Under Min (AUM) of false positive and false negative rates has been proposed as a differentiable surrogate for AUC. In this paper we study the piecewise linear/constant nature of the AUM/AUC, and propose new efficient path-following algorithms for choosing the learning rate which is optimal for each step of gradient descent (line search), when optimizing a linear model. Remarkably, our proposed line search algorithm has the same log-linear asymptotic time complexity as gradient descent with constant step size, but it computes a complete representation of the AUM/AUC as a function of step size. In our empirical study of binary classification problems, we verify that our proposed algorithm is fast and exact; in changepoint detection problems we show that the proposed algorithm is just as accurate as grid search, but faster.

Machine learning techniques have recently been of great interest for solving differential equations. Training these models is classically a data-fitting task, but knowledge of the expression of the differential equation can be used to supplement the training objective, leading to the development of physics-informed scientific machine learning. In this article, we focus on one class of models called nonlinear vector autoregression (NVAR) to solve ordinary differential equations (ODEs). Motivated by connections to numerical integration and physics-informed neural networks, we explicitly derive the physics-informed NVAR (piNVAR) which enforces the right-hand side of the underlying differential equation regardless of NVAR construction. Because NVAR and piNVAR completely share their learned parameters, we propose an augmented procedure to jointly train the two models. Then, using both data-driven and ODE-driven metrics, we evaluate the ability of the piNVAR model to predict solutions to various ODE systems, such as the undamped spring, a Lotka-Volterra predator-prey nonlinear model, and the chaotic Lorenz system.

The game Assassin's Creed fans have been asking for years is finally on its way. During its Ubisoft Forward event on Saturday, the publisher revealed Codename Red, a new entry in the series that will be set in feudal Japan. Franchise head Marc-Alexis Côté called Red the "next premium title" in Ubisoft's open world series and said Ubisoft Quebec was leading work on the project, suggesting it will hew closer to Odyssey than next year's Mirage. Côté also shared a teaser for Codename Hexe and called it "a very different type of Assassin's Creed game." Ubisoft Montreal, the studio that first created the series is leading development on the project, with Clint Hocking involved as creative director.

WellSaid Labs, whose tools create synthetic speech that could be mistaken for the real thing, has raised a $10M Series A to grow the business. The company's home-baked text-to-speech engine works faster than real time and produces natural-sounding clips of pretty much any length, from quick snippets to hours-long readings. WellSaid came out of the Allen Institute for AI incubator in 2019, and its goal was to make synthetic voices that didn't sound so robotic for common business purposes like training and marketing content. It achieved that first by basing its solution on Tacotron, a speech engine developed by Google and academic researchers. But soon it had built its own that was more efficient, resulted in more convincing voices, and could produce clips of arbitrary lengths.

Back in 2015, when creative director Clint Hocking and his team began crafting the near-future world of Watch Dogs: Legion, some of the biggest technology companies in the world were confidently describing skies buzzing with package-delivery drones and streets alive with autonomous vehicles. Into the game they went. For a speculative fiction game about mass surveillance, that creates some problems. "Technology companies--Tesla, Amazon--had started talking publicly about pretty aggressive timelines, schedules, and regulations," Hocking said in an interview with WIRED. On October 29, Watch Dogs: Legion will release as both a game and a time capsule from 2015, back when a couple of big, stock-inflating daydreams painted a picture for 2020 that's still far from materializing.

Clint Hocking marked his return to Ubisoft in 2015 with a big idea. His new project "Watch Dogs: Legion" was ambitious, and its concept was born from a single question: What if you could play as anyone? It had never been done before. In open-world games, players normally control a single protagonist, or a couple of carefully crafted main characters. But Hocking envisioned a Watch Dogs game where players could explore a metropolitan city and, with the press of a button, switch perspectives to inhabit the body of a spy, construction worker or an average Joe walking to their office job. Every passerby is their own person, primed with a web of relationships, an occupation and a personality.

Armed militia stroll around London, picking fights where they please and shutting down small gatherings of masked protesters demanding their freedoms on street corners. In Watch Dogs Legion's future dystopian British capital, Brexit happened years ago, Scotland has seceded from the union, and the country has been overtaken by private, corporate interests who've wrested control from the government and framed a collective of hacker protesters, DeadSec, for a series of terrorist attacks. People are pissed off, and ready to rise up. You, the player, are the catalyst that makes that happen. Like Grand Theft Auto, Watch Dogs conjures a huge living city out of code, filled with thousands of individual characters who go about their lives, going to work, visiting their sister, driving around in the rain.

Do you know why your CMO needs artificial intelligence NOW? Because: CMOs must show measurable financial results for the budget they invested! Wonder how AI relates to financial results? I'm not surprised since the answer may not be obvious. With an ever-increasing number of smart devices, apps and methods, consumers have more and more ways to get information and create content digitally. In the process, they create an explosion of data for marketers to track and analyze.

Stunning footage has revealed the first evidence that leopard seals share food -- with the marine mammals caught divvying up a penguin as they feast on their kill. The ground-breaking footage was captured by a drone flying off the coast of the island of South Georgia, in the southern Atlantic. Researchers said that leopard seals are normally regarded as being solitary creatures. The Antarctic predators are largely'intolerant' of each other, but can be forced to hunt alongside each another when congregating in areas of plentiful prey, the experts added. The leopard seal is named for its black-spotted coat, whose pattern is similar to that of the big cat, though the seal's coat is grey rather than golden in colour.