While artificial intelligence offers opportunities to automate and innovate, just 30% of workplaces are actually using it. Combined with a lack of understanding of the technology, employers don't have the internal structure and personnel needed to launch the power of AI into their business model, says Augustine Walker, senior director of product management for Veritone, an AI solutions provider. "There isn't a lot of focus on what tools are out there so that I can make my business better with AI," Walker says. "The ubiquity of the talent pool and the capabilities are not out there yet -- it's still maturing." Walker spoke with Employee Benefit News on how AI can actually be a catalyst for creativity and why data scientists are a critical piece to the puzzle.

Automating molecular design using deep reinforcement learning (RL) holds the promise of accelerating the discovery of new chemical compounds. A limitation of existing approaches is that they work with molecular graphs and thus ignore the location of atoms in space, which restricts them to 1) generating single organic molecules and 2) heuristic reward functions. To address this, we present a novel RL formulation for molecular design in Cartesian coordinates, thereby extending the class of molecules that can be built. Our reward function is directly based on fundamental physical properties such as the energy, which we approximate via fast quantum-chemical methods. To enable progress towards de-novo molecular design, we introduce MolGym, an RL environment comprising several challenging molecular design tasks along with baselines. In our experiments, we show that our agent can efficiently learn to solve these tasks from scratch by working in a translation and rotation invariant state-action space.

The European Patent Office recently turned down an application for a patent that described a food container. This was not because the invention was not novel or useful, but because it was created by artificial intelligence. By law, inventors need to be actual people. This isn't the first invention by AI – machines have produced innovations ranging from scientific papers and books to new materials and music. That said, being creative is clearly one of the most remarkable human traits.

Natural sounds are structured on many time-scales. A typical segment of speech, for example, contains features that span four orders of magnitude: Sentences ( 1s); phonemes ( 0.1s); glottal pulses ( 0.01s); and formants ( 0.001s). The auditory system uses information from each of these time-scales to solve complicated tasks such as auditory scene analysis. One route toward understanding how auditory processing accomplishes this analysis is to build neuroscience-inspired algorithms which solve similar tasks and to compare the properties of these algorithms with properties of auditory processing. There is however a discord: Current machine-audition algorithms largely concentrate on the shorter time-scale structures in sounds, and the longer structures are ignored.

We introduce a generic scheme for accelerating first-order optimization methods in the sense of Nesterov, which builds upon a new analysis of the accelerated proximal point algorithm. Our approach consists of minimizing a convex objective by approximately solving a sequence of well-chosen auxiliary problems, leading to faster convergence. This strategy applies to a large class of algorithms, including gradient descent, block coordinate descent, SAG, SAGA, SDCA, SVRG, Finito/MISO, and their proximal variants. For all of these methods, we provide acceleration and explicit support for non-strongly convex objectives. In addition to theoretical speed-up, we also show that acceleration is useful in practice, especially for ill-conditioned problems where we measure significant improvements.

The aging adage, "there's an app for that," is evolving into, "there's a robot for that." More and more automation is finding its way to the market for household chores like cleaning floors, and now that innovation is in farmer's fields with Odd.Bot, an automatic weeding robot. Odd.Bot made an appearance at the Consumer Electronics Show (CES) in Las Vegas last month with an informational booth and the weed-plucking device on display. Martijn Lukaart, Founder and CEO, explains that Odd.Bot is currently intended for use in organic farming fields to make the weed-pulling process easier for large farms who currently do all the work by hand. Many large-scale farmers have already invested in a platform that allows workers to lay face down on a bed as they are propelled through the rows of crops.

The European Patent Office recently turned down an application for a patent that described a food container. This was not because the invention was not novel or useful, but because it was created by artificial intelligence (AI). By law, inventors need to be actual people. This isn't the first invention by AI – machines have produced innovations ranging from scientific papers and books to new materials and music. That said, being creative is clearly one of the most remarkable human traits.

Steel is the world's most popular construction material because of its unique combination of durability, workability, and cost. Methods for manufacturing steel have evolved significantly since industrial production began in the late 19th century. Today, steel production makes use of recycled materials. A top U.S. steel manufacturer, "Metals, Inc.," (name withheld) purchases scrap metal and melts it into steel billets either to sell or to cast into other finished goods for sale. Despite the high stakes, the quality measurements for each batch are not available until the last few minutes in the 90-minute melting process.

The European Patent Office recently turned down an application for a patent that described a food container. This was not because the invention was not novel or useful, but because it was created by artificial intelligence (AI). By law, inventors need to be actual people. This isn't the first invention by AI – machines have produced innovations ranging from scientific papers and books to new materials and music. That said, being creative is clearly one of the most remarkable human traits.

By accurately predicting industrial aging processes (IAPs), it is possible to schedule maintenance events further in advance, thereby ensuring a cost-efficient and reliable operation of the plant. So far, these degradation processes were usually described by mechanistic models or simple empirical prediction models. In this paper, we evaluate a wider range of data-driven models for this task, comparing some traditional stateless models (linear and kernel ridge regression, feed-forward neural networks) to more complex recurrent neural networks (echo state networks and LSTMs). To examine how much historical data is needed to train each of the models, we first examine their performance on a synthetic dataset with known dynamics. Next, the models are tested on real-world data from a large scale chemical plant. Our results show that LSTMs produce near perfect predictions when trained on a large enough dataset, while linear models may generalize better given small datasets with changing conditions.