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.

UNIVERSITY PARK, Pa.-- Enrique Del Castillo, distinguished professor of industrial engineering and professor of statistics at Penn State, has returned from his Fulbright U.S. Scholar Program, where he conducted research at the University of Coimbra in Coimbra, Portugal. Awarded by the J. William Fulbright Foreign Scholarship Board, Del Castillo was one of approximately 800 U.S. citizens selected to take their expertise abroad for the 2019-20 academic year through the program. Recipients of Fulbright Awards are selected on the basis of academic and professional achievement, as well as record of service and demonstrated leadership in their respective fields. The research project for which he was granted the Fulbright Fellowship, titled "Optimization and control of industrial production processes by active learning methods based on'big' and complex data," sought collaborative research between Penn State's Engineering Statistics and Machine Learning Laboratory and the University of Coimbra's chemometrics group in the Department of Chemical Engineering. Del Castillo worked on the optimization of production processes via machine learning for various industries with the chemometrics group; in particular, they focused on wine, paper and pharmaceuticals.

Optical Wireless Communication (OWC) propagation channel characterization plays a key role on the design and performance analysis of Vehicular Visible Light Communication (VVLC) systems. Current OWC channel models based on deterministic and stochastic methods, fail to address mobility induced ambient light, optical turbulence and road reflection effects on channel characterization. Therefore, alternative machine learning (ML) based schemes, considering ambient light, optical turbulence, road reflection effects in addition to intervehicular distance and geometry, are proposed to obtain accurate VVLC channel loss and channel frequency response (CFR). This work demonstrates synthesis of ML based VVLC channel model frameworks through multi layer perceptron feed-forward neural network (MLP), radial basis function neural network (RBF-NN) and Random Forest ensemble learning algorithms. Predictor and response variables, collected through practical road measurements, are employed to train and validate proposed models for various conditions. Additionally, the importance of different predictor variables on channel loss and CFR is assessed, normalized importance of features for measured VVLC channel is introduced. We show that RBF-NN, Random Forest and MLP based models yield more accurate channel loss estimations with 3.53 dB, 3.81 dB, 3.95 dB root mean square error (RMSE), respectively, when compared to fitting curve based VVLC channel model with 7 dB RMSE. Moreover, RBF-NN and MLP models are demonstrated to predict VVLC CFR with respect to distance, ambient light and receiver inclination angle predictor variables with 3.78 dB and 3.60 dB RMSE respectively.

Recently, there have been significant interests in studying the generalization power of linear regression models in the overparameterized regime, with the hope that such analysis may provide the first step towards understanding why overparameterized deep neural networks generalize well even when they overfit the training data. Studies on min $\ell_2$-norm solutions that overfit the training data have suggested that such solutions exhibit the "double-descent" behavior, i.e., the test error decreases with the number of features $p$ in the overparameterized regime when $p$ is larger than the number of samples $n$. However, for linear models with i.i.d. Gaussian features, for large $p$ the model errors of such min $\ell_2$-norm solutions approach the "null risk," i.e., the error of a trivial estimator that always outputs zero, even when the noise is very low. In contrast, we studied the overfitting solution of min $\ell_1$-norm, which is known as Basis Pursuit (BP) in the compressed sensing literature. Under a sparse true linear model with i.i.d. Gaussian features, we show that for a large range of $p$ up to a limit that grows exponentially with $n$, with high probability the model error of BP is upper bounded by a value that decreases with $p$ and is proportional to the noise level. To the best of our knowledge, this is the first result in the literature showing that, without any explicit regularization in such settings where both $p$ and the dimension of data are much larger than $n$, the test errors of a practical-to-compute overfitting solution can exhibit double-descent and approach the order of the noise level independently of the null risk. Our upper bound also reveals a descent floor for BP that is proportional to the noise level. Further, this descent floor is independent of $n$ and the null risk, but increases with the sparsity level of the true model.