Reservoir Computing with Cellular Automata (ReCA) is a relatively novel and promising approach. It consists of 3 steps: an encoding scheme to inject the problem into the CA, the CA iterations step itself and a simple classifying step, typically a linear classifier. This paper demonstrates that the ReCA concept is effective even in arguably the simplest implementation of a ReCA system. However, we also report a failed attempt on the UCR Time Series Classification Archive where ReCA seems to work, but only because of the encoding scheme itself, not in any part due to the CA. This highlights the need for ablation testing, i.e., comparing internally with sub-parts of one model, but also raises an open question on what kind of tasks ReCA is best suited for.

Solving parametric Partial Differential Equations (PDEs) for a broad range of parameters is a critical challenge in scientific computing. To this end, neural operators, which learn mappings from parameters to solutions, have been successfully used. However, the training of neural operators typically demands large training datasets, the acquisition of which can be prohibitively expensive. To address this challenge, physics-informed training can offer a cost-effective strategy. However, current physics-informed neural operators face limitations, either in handling irregular domain shapes or in generalization to various discretizations of PDE parameters with variable mesh sizes. In this research, we introduce a novel physics-informed model architecture which can generalize to parameter discretizations of variable size and irregular domain shapes. Particularly, inspired by deep operator neural networks, our model involves a discretization-independent learning of parameter embedding repeatedly, and this parameter embedding is integrated with the response embeddings through multiple compositional layers, for more expressivity. Numerical results demonstrate the accuracy and efficiency of the proposed method.

We demonstrate a successful navigation and docking control system for the John Deere Tango autonomous mower, using only a single camera as the input. This vision-only system is of interest because it is inexpensive, simple for production, and requires no external sensing. This is in contrast to existing systems that rely on integrated position sensors and global positioning system (GPS) technologies. To produce our system we combined a state-of-the-art object detection architecture, YOLO, with a reinforcement learning (RL) architecture, Double Deep QNetworks (Double DQN). The object detection network identifies features on the mower and passes its output to the RL network, providing it with a low-dimensional representation that enables rapid and robust training. Finally, the RL network learns how to navigate the machine to the desired spot in a custom simulation environment. When tested on mower hardware the system is able to dock with centimeter-level accuracy from arbitrary initial locations and orientations.

We study the convergence rates of empirical Bayes posterior distributions for nonparametric and high-dimensional inference. We show that as long as the hyperparameter set is discrete, the empirical Bayes posterior distribution induced by the maximum marginal likelihood estimator can be regarded as a variational approximation to a hierarchical Bayes posterior distribution. This connection between empirical Bayes and variational Bayes allows us to leverage the recent results in the variational Bayes literature, and directly obtains the convergence rates of empirical Bayes posterior distributions from a variational perspective. For a more general hyperparameter set that is not necessarily discrete, we introduce a new technique called "prior decomposition" to deal with prior distributions that can be written as convex combinations of probability measures whose supports are low-dimensional subspaces. This leads to generalized versions of the classical "prior mass and testing" conditions for the convergence rates of empirical Bayes. Our theory is applied to a number of statistical estimation problems including nonparametric density estimation and sparse linear regression.

Victoria Stodden (vcs@stodden.net) is a statistician and associate professor at the University of Illinois at Urbana-Champaign, IL, USA. This material is based upon work supported by National Science Foundation Award #1941443.

Romit Roy Choudhury is a professor and Jerry Sanders III AMD Inc. Scholar in the Department of ECE and CS at the University of Illinois at Urbana-Champaign, IL, USA. To view the accompanying paper, visit doi.acm.org/10.1145/3236621

Romit Roy Choudhury is a professor and Jerry Sanders III AMD Inc. Scholar in the Department of ECE and CS at the University of Illinois at Urbana-Champaign, IL, USA. To view the accompanying paper, visit doi.acm.org/10.1145/3236621

Human Interact is a VR storytelling startup based in Champaign, Illinois, and Starship Commander is one their newest VR games. One of the goals for Alexander Mejia and Adam Nydahl, the storytellers behind Starship Commander, was to use the easiest controller of them all – the human voice. However, the world they were crafting was full of fictional names and phrases which most existing cloud based solutions failed to understand. So they were on the lookout for a more accurate speech recognition platform. That's when Mejia and Nydahl became aware of Microsoft's Cognitive Services, offering developers Artificial Intelligence technologies spanning vision, speech, language, and knowledge, all accessible with just a few lines of code.