We introduce AndroidEnv, an open-source platform for Reinforcement Learning (RL) research built on top of the Android ecosystem. AndroidEnv allows RL agents to interact with a wide variety of apps and services commonly used by humans through a universal touchscreen interface. Since agents train on a realistic simulation of an Android device, they have the potential to be deployed on real devices. In this report, we give an overview of the environment, highlighting the significant features it provides for research, and we present an empirical evaluation of some popular reinforcement learning agents on a set of tasks built on this platform.

Federal agencies are getting better at buying advanced technologies like artificial intelligence but still lag in deploying those tools due to security concerns, according to a Homeland Security Department procurement official. "We're doing a really good job at procuring things," Jessica Clark, an official on the Acquisition Systems Team in DHS's Office of the Chief Procurement Officer, said Tuesday during the Professional Services Council's annual Tech Trends conference. "But getting it up and running safely is always going to be an issue for our program managers." Clark said DHS takes a different procurement strategy when looking at new and innovative technologies, preferring a phased approach where a relatively large pool of vendors is whittled down over the course of multiple prototypes and demonstrations, with each subsequent phase using larger datasets that are more and more relevant to the program. She cited the department's work integrating AI into the Contractor Performance Assessment Reporting System, or CPARS, which contracting officers use to gauge a vendor's past performance on government contracts. For the CPARS AI effort, DHS started with nine vendors, which was then down-selected to six and then four.

In the last years, artificial neural networks (ANN) have successfully been applied across a number of tasks, such as image classification, speech recognition and natural language understanding. Two main drivers, firstly a large amount of (labelled) data, and secondly growing compute resources, allowed to use technology that dates back to the 1960s and break records on many benchmarks. However, designing well-performing ANNs requires expert knowledge and experience. Neuroevolution aims at solving this difficult and often time-consuming process by applying evolutionary techniques. This article aims to provide an introduction to the re-emerging field of neuroevolution by supplying a definition, differentiating between other fields and areas and giving an overview by summarising a number of recent research papers. Inspired by biological neural networks, ANNs consist of many artificial neurons that are connected to each other. In a process, mostly referred to as training or learning, ANNs are optimised to solve specific, predefined tasks such as detecting faces. Learning is usually realised by employing a form of stochastic gradient descent (SGD) in order to change the network parameters in such a way that a future prediction for the same input is closer to the desired output. The architecture of a network, i.e. how the neurons are connected to each other, plays a very important role in whether or not an ANN can be trained to successfully learn a task. Over the years, human experts carefully designed complex architectures such as the VGGNet, AlexNet, GoogleNet, ResNet and many more to achieve and often surpass human-level performance on many different tasks.

A community reveals the features and connections of its members that are different from those in other communities in a network. Detecting communities is of great significance in network analysis. Despite the classical spectral clustering and statistical inference methods, we notice a significant development of deep learning techniques for community detection in recent years with their advantages in handling high dimensional network data. Hence, a comprehensive overview of community detection's latest progress through deep learning is timely to both academics and practitioners. This survey devises and proposes a new taxonomy covering different categories of the state-of-the-art methods, including deep learning-based models upon deep neural networks, deep nonnegative matrix factorization and deep sparse filtering. The main category, i.e., deep neural networks, is further divided into convolutional networks, graph attention networks, generative adversarial networks and autoencoders. The survey also summarizes the popular benchmark data sets, model evaluation metrics, and open-source implementations to address experimentation settings. We then discuss the practical applications of community detection in various domains and point to implementation scenarios. Finally, we outline future directions by suggesting challenging topics in this fast-growing deep learning field.

Transportation services play a crucial part in the development of modern smart cities. In particular, on-demand ridesharing services, which group together passengers with similar itineraries, are already operating in several metropolitan areas. These services can be of significant social and environmental benefit, by reducing travel costs, road congestion and CO2 emissions. Unfortunately, despite their advantages, not many people opt to use these ridesharing services. We believe that increasing the user satisfaction from the service will cause more people to utilize it, which, in turn, will improve the quality of the service, such as the waiting time, cost, travel time, and service availability. One possible way for increasing user satisfaction is by providing appropriate explanations comparing the alternative modes of transportation, such as a private taxi ride and public transportation. For example, a passenger may be more satisfied from a shared-ride if she is told that a private taxi ride would have cost her 50% more. Therefore, the problem is to develop an agent that provides explanations that will increase the user satisfaction. We model our environment as a signaling game and show that a rational agent, which follows the perfect Bayesian equilibrium, must reveal all of the information regarding the possible alternatives to the passenger. In addition, we develop a machine learning based agent that, when given a shared-ride along with its possible alternatives, selects the explanations that are most likely to increase user satisfaction. Using feedback from humans we show that our machine learning based agent outperforms the rational agent and an agent that randomly chooses explanations, in terms of user satisfaction.

Building machine learning models using EEG recorded outside of the laboratory setting requires methods robust to noisy data and randomly missing channels. This need is particularly great when working with sparse EEG montages (1-6 channels), often encountered in consumer-grade or mobile EEG devices. Neither classical machine learning models nor deep neural networks trained end-to-end on EEG are typically designed or tested for robustness to corruption, and especially to randomly missing channels. While some studies have proposed strategies for using data with missing channels, these approaches are not practical when sparse montages are used and computing power is limited (e.g., wearables, cell phones). To tackle this problem, we propose dynamic spatial filtering (DSF), a multi-head attention module that can be plugged in before the first layer of a neural network to handle missing EEG channels by learning to focus on good channels and to ignore bad ones. We tested DSF on public EEG data encompassing ~4,000 recordings with simulated channel corruption and on a private dataset of ~100 at-home recordings of mobile EEG with natural corruption. Our proposed approach achieves the same performance as baseline models when no noise is applied, but outperforms baselines by as much as 29.4% accuracy when significant channel corruption is present. Moreover, DSF outputs are interpretable, making it possible to monitor channel importance in real-time. This approach has the potential to enable the analysis of EEG in challenging settings where channel corruption hampers the reading of brain signals.

While the choice of prior is one of the most critical parts of the Bayesian inference workflow, recent Bayesian deep learning models have often fallen back on vague priors, such as standard Gaussians. In this review, we highlight the importance of prior choices for Bayesian deep learning and present an overview of different priors that have been proposed for (deep) Gaussian processes, variational autoencoders, and Bayesian neural networks. We also outline different methods of learning priors for these models from data. We hope to motivate practitioners in Bayesian deep learning to think more carefully about the prior specification for their models and to provide them with some inspiration in this regard.

We spoke about how humans can easily locate where to take a step but how would numbers do this? How would numbers where the downward direction is? Above, we have a cost J which is a function of only one parameter w. This function can be represented through an equation in terms of w. To update w in order to reduce J we first start with a random value of w and then update the value using this equation. Here alpha is the learning rate we spoke about.

Sustainable finance technology solutions provider Arabesque announced a series of high-profile senior appointments today, including the addition of former Deutsche Bank CEO Jürgen Fitschen to the board of AI-based sustainability data and insights services provider Arabesque S-Ray. Additionally, the company has appointed former Allianz COO Dr Christof Mascher and Dr Lars Jaeger, the head of Alternative Risk Premia at GAM Systematic, to the Senior Advisor Committee of AI-based portfolio management tool provider Arabesque AI. "Arabesque is on a path to help transform finance and industry by the intelligent application of market-leading sustainability know-how and innovative technology. It's an approach based on the understanding that ESG and AI will re-shape the global marketplace over the next decade." "I am delighted to welcome Mr Fitschen, Dr Mascher and Dr Jaeger as new Senior Independent Advisors at Arabesque, all three of them global leaders in their field with exceptional careers. Their wealth of experience at the forefront of finance and digital transformation will be invaluable as we grow to become the leading sustainable technology company."

For the insurance industry, the health and safety benefits of wearables and other IoT-connected devices is well established. But meeting new customer demands for protection goes beyond capturing user-generated data. What matters now is how an insurer and their ecosystem partners use the data shared with them by the customer. And whether they have the right mix of talent and technology to optimize its use. Analytics capabilities, including predictive and prescriptive analytics, can enable data-driven insurance offers in real-time.