A Swedish man discovered the 12th century buried treasure near his summer home. Breakthroughs, discoveries, and DIY tips sent every weekday. It only costs a few dollars to buy a tub of bait worms for fishing, but many people are fine with sourcing them straight from the ground. There's always a chance you may find more in the dirt than wriggling invertebrates. Take a recent example near Stockholm, Sweden: According to county officials last month, an unnamed fisherman scrounging for worms at his summer house discovered a corroded copper cauldron containing around 13 pounds of treasure from the Middle Ages.

Bayesian optimization (BO) is a popular approach for sample-efficient optimization of black-box objective functions. While BO has been successfully applied to a wide range of scientific applications, traditional approaches to single-objective BO only seek to find a single best solution. This can be a significant limitation in situations where solutions may later turn out to be intractable. For example, a designed molecule may turn out to violate constraints that can only be reasonably evaluated after the optimization process has concluded. To address this issue, we propose Rank-Ordered Bayesian Optimization with Trust-regions (ROBOT) which aims to find a portfolio of high-performing solutions that are diverse according to a user-specified diversity metric. We evaluate ROBOT on several real-world applications and show that it can discover large sets of high-performing diverse solutions while requiring few additional function evaluations compared to finding a single best solution.

Fox News correspondent Grady Trimble has the latest on fears the technology will spiral out of control on'Special Report.' As the world of artificial intelligence blooms, some players in the health care industry are looking to make a major difference in public health. HMNC Brain Health -- a Munich, Germany-based health tech company -- is one of those. It's attempting to use novel AI-powered technologies to address mental health issues. The company has developed what's described as a "precision psychiatry" diagnostic tool that uses artificial intelligence to predict, diagnose and even treat depression.

In this paper, we study the problem of transferring the available Markov Decision Process (MDP) models to learn and plan efficiently in an unknown but similar MDP. We refer to it as \textit{Model Transfer Reinforcement Learning (MTRL)} problem. First, we formulate MTRL for discrete MDPs and Linear Quadratic Regulators (LQRs) with continuous state actions. Then, we propose a generic two-stage algorithm, MLEMTRL, to address the MTRL problem in discrete and continuous settings. In the first stage, MLEMTRL uses a \textit{constrained Maximum Likelihood Estimation (MLE)}-based approach to estimate the target MDP model using a set of known MDP models. In the second stage, using the estimated target MDP model, MLEMTRL deploys a model-based planning algorithm appropriate for the MDP class. Theoretically, we prove worst-case regret bounds for MLEMTRL both in realisable and non-realisable settings. We empirically demonstrate that MLEMTRL allows faster learning in new MDPs than learning from scratch and achieves near-optimal performance depending on the similarity of the available MDPs and the target MDP.

The plans that planning systems generate for solvable planning tasks are routinely verified by independent validation tools. For unsolvable planning tasks, no such validation capabilities currently exist. We describe a family of certificates of unsolvability for classical planning tasks that can be efficiently verified and are sufficiently general for a wide range of planning approaches including heuristic search with delete relaxation, critical-path, pattern database and linear merge-and-shrink heuristics, symbolic search with binary decision diagrams, and the Trapper algorithm for detecting dead ends. We also augmented a classical planning system with the ability to emit certificates of unsolvability and implemented a planner-independent certificate validation tool. Experiments show that the overhead for producing such certificates is tolerable and that their validation is practically feasible.

While traditionally classical planning concentrated on finding plans for solvable tasks, detecting unsolvable instances has recently attracted increasing interest. To preclude wrong results, it is desirable that the planning system provides a certificate of unsolvability that can be independently verified. We propose a rule-based proof system for unsolvability where a proof establishes a knowledge base of verifiable basic statements and applies a set of derivation rules to infer the unsolvability of the task from these statements. We argue that this approach is more flexible than a recent proposal of inductive certificates of unsolvability and show how our proof system can be used for a wide range of planning techniques.

We study the problem of performing automated experiment design for drug screening through Bayesian inference and optimisation. In particular, we compare and contrast the behaviour of linear-Gaussian models and Gaussian processes, when used in conjunction with upper confidence bound algorithms, Thompson sampling, or bounded horizon tree search. We show that non-myopic sophisticated exploration techniques using sparse tree search have a distinct advantage over methods such as Thompson sampling or upper confidence bounds in this setting. We demonstrate the significant superiority of the approach over existing and synthetic datasets of drug toxicity.

One of the suits of armor available in Assassin's Creed: Valhalla -- if you're willing to pay realn money. One of the suits of armor available in Assassin's Creed: Valhalla -- if you're willing to pay realn money. Assassin's Creed Valhalla, the latest installment in Ubisoft's Assassin's Creed franchise, came out in November 2020. Like most AC games, it was highly anticipated; it sold more copies in its opening week than any other game in the series. Needless to say, fans were excited.

Recently, IndustryWeek hosted a PTC-sponsored webinar called Pragmatic Paths to Accelerate Manufacturing Performance with Industrie 4.0. The presenters, Kent Eriksson, a Senior Advisor in PTC's IoT Transformation Advisory Practice, and Stephen Laaper, a Digital Supply Networks leader in Deloitte Consulting's Strategy & Operations practice, had too much information about the best, most practical ways to adopt the Industrial Internet of Things (IIoT) didn't have time to answer every listeners' questions. It's such a vital component to the future of manufacturing success, one that there is much to learn about, that we all felt these questions could not linger. So here they are, and even if you couldn't attend, there is much to glean from these experts' responses. Q: Where should we draw distinctions between Industrie 4.0 and IoT, and Big Data and its connectors?

Ever since the first artificial neural network was built in 1951 by researchers at MIT, artificial intelligence has gradually muscled its way into a wide range of areas: video games, search engines, healthcare, smartphones, and transport. AI programs have already learnt how to imitate Bach and the Beatles, and at the end of last year, researchers even trained a neural network to produce "original" metal in the vein of Krallice, Meshuggah, and the Dillinger Escape Plan. Yet while the doom-mongers are predicting that even human creativity will eventually be made obsolete by robots, a growing wave of artists are using AI and algorithms to take their own music in new and exciting directions. Some are using machine learning to teach software to compose music they later play themselves, while others are using live coding to program electronic music that's improvisational, unpredictable, and surprisingly human. Either way, the 10 artists in this list are not only harnessing high-technology to make unique and progressive music, they're also showing how the rise of AI doesn't necessarily mean the death of creativity. One of last year's best examples of live coding, Belisha Beacon's debut This Is Fine uses the ixi lang programming language to create minimal, looping techno.