When you're shopping, you probably have a general look in mind. But how do you describe that to a shopping site? It's implementing a feature that uses computer vision to find items that resemble what you're looking at. Tap the three-dot menu next to a product and it'll give you both simple category buttons (such as "athletic shoes") as well as a "looks like this" option to find visually similar items. Eye a green set of sneakers, for instance, and you should see comparable footwear without having to construct an elaborate search. This AI-guided shopping is available in eBay's Android and iOS apps right now, though it's currently only available in the US, UK, Australia and Germany.

The Absorption, Distribution, Metabolism, Elimination, and Toxicity (ADMET) properties of drug candidates are estimated to account for up to 50% of all clinical trial failures. Predicting ADMET properties has therefore been of great interest to the cheminformatics and medicinal chemistry communities in recent decades. Traditional cheminformatics approaches, whether the learner is a random forest or a deep neural network, leverage fixed fingerprint feature representations of molecules. In contrast, in this paper, we learn the features most relevant to each chemical task at hand by representing each molecule explicitly as a graph, where each node is an atom and each edge is a bond. By applying graph convolutions to this explicit molecular representation, we achieve, to our knowledge, unprecedented accuracy in prediction of ADMET properties. By challenging our methodology with rigorous cross-validation procedures and prospective analyses, we show that deep featurization better enables molecular predictors to not only interpolate but also extrapolate to new regions of chemical space.

Off-Policy reinforcement learning (RL) is an important class of methods for many problem domains, such as robotics, where the cost of collecting data is high and on-policy methods are consequently intractable. Standard methods for applying Q-learning to continuous-valued action domains involve iteratively sampling the Q-function to find a good action (e.g. via hill-climbing), or by learning a policy network at the same time as the Q-function (e.g. DDPG). Both approaches make tradeoffs between stability, speed, and accuracy. We propose a novel approach, called Cross-Entropy Guided Policies, or CGP, that draws inspiration from both classes of techniques. CGP aims to combine the stability and performance of iterative sampling policies with the low computational cost of a policy network. Our approach trains the Q-function using iterative sampling with the Cross-Entropy Method (CEM), while training a policy network to imitate CEM's sampling behavior. We demonstrate that our method is more stable to train than state of the art policy network methods, while preserving equivalent inference time compute costs, and achieving competitive total reward on standard benchmarks.

Humans tend to learn complex abstract concepts faster if examples are presented in a structured manner. For instance, when learning how to play a board game, usually one of the first concepts learned is how the game ends, i.e. the actions that lead to a terminal state (win, lose or draw). The advantage of learning end-games first is that once the actions which lead to a terminal state are understood, it becomes possible to incrementally learn the consequences of actions that are further away from a terminal state - we call this an end-game-first curriculum. Currently the state-of-the-art machine learning player for general board games, AlphaZero by Google DeepMind, does not employ a structured training curriculum; instead learning from the entire game at all times. By employing an end-game-first training curriculum to train an AlphaZero inspired player, we empirically show that the rate of learning of an artificial player can be improved during the early stages of training when compared to a player not using a training curriculum.

For sampling from a log-concave density, we study implicit integrators resulting from $\theta$-method discretization of the overdamped Langevin diffusion stochastic differential equation. Theoretical and algorithmic properties of the resulting sampling methods for $ \theta \in [0,1] $ and a range of step sizes are established. Our results generalize and extend prior works in several directions. In particular, for $\theta\ge1/2$, we prove geometric ergodicity and stability of the resulting methods for all step sizes. We show that obtaining subsequent samples amounts to solving a strongly-convex optimization problem, which is readily achievable using one of numerous existing methods. Numerical examples supporting our theoretical analysis are also presented.

Deep Learning (DL) has had an immense success in the recent past, leading to state-of-the-art results in various domains such as image recognition and natural language processing. One of the reasons for this success is the increasing size of DL models and the proliferation of vast amounts of training data being available. To keep on improving the performance of DL, increasing the scalability of DL systems is necessary. In this survey, we perform a broad and thorough investigation on challenges, techniques and tools for scalable DL on distributed infrastructures. This incorporates infrastructures for DL, methods for parallel DL training, multi-tenant resource scheduling and the management of training and model data. Further, we analyze and compare 11 current open-source DL frameworks and tools and investigate which of the techniques are commonly implemented in practice. Finally, we highlight future research trends in DL systems that deserve further research.

In the first days after a fleet of 25 delivery robots descended on George Mason University's campus in January, school officials could only speculate about the machines' long-term impact. The Igloo cooler-sized robots from the Bay Area start-up Starship Technologies -- which were designed to deliver food on demand across campus -- appeared to elicit curious glances and numerous photos, but not much else. It was clear, officials said at the time, that more time and more data would be necessary to understand whether the robots would actually change the campus culture or become a forgettable novelty. Today, some of that data emerged for the first time. In the two months since the robots arrived at the Fairfax, Va.-based school, an extra 1,500 breakfast orders have been delivered autonomously, according to Starship Technologies and Sodexo, a company that manages food services for GMU on contract and works closely with the robots.

Fuzzy systems have achieved great success in numerous applications. However, there are still many challenges in designing an optimal fuzzy system, e.g., how to efficiently train its parameters, how to improve its performance without adding too many parameters, how to balance the trade-off between cooperations and competitions among the rules, how to overcome the curse of dimensionality, etc. Literature has shown that by making appropriate connections between fuzzy systems and other machine learning approaches, good practices from other domains may be used to improve the fuzzy systems, and vice versa. This paper gives an overview on the functional equivalence between Takagi-Sugeno-Kang fuzzy systems and four classic machine learning approaches -- neural networks, mixture of experts, classification and regression trees, and stacking ensemble regression -- for regression problems. We also point out some promising new research directions, inspired by the functional equivalence, that could lead to solutions to the aforementioned problems. To our knowledge, this is so far the most comprehensive overview on the connections between fuzzy systems and other popular machine learning approaches, and hopefully will stimulate more hybridization between different machine learning algorithms.

Predictive analytics systems are currently one of the most important areas of research and development within the Artificial Intelligence domain and particularly in Machine Learning. One of the "holy grails" of predictive analytics is the research and development of the "perfect" recommendation system. In our paper we propose an advanced pipeline model for the multi-task objective of determining product complementarity, similarity and sales prediction using deep neural models applied to big-data sequential transaction systems. Our highly parallelized hybrid pipeline consists of both unsupervised and supervised models, used for the objectives of generating semantic product embeddings and predicting sales, respectively. Our experimentation and benchmarking have been done using very large pharma-industry retailer Big Data stream.

Facebook said on Wednesday night that its artificial intelligence systems failed to automatically detect the New Zealand mosque shooting video. A senior executive at the social media giant responded in a blog post to criticism that it didn't act quickly enough to take down the gunman's livestream video of his attack in Christchurch that left 50 people dead, allowing it to spread rapidly online. Facebook's vice president of integrity, Guy Rosen, said "this particular video did not trigger our automatic detection systems." "AI has made massive progress over the years and in many areas, which has enabled us to proactively detect the vast majority of the content we remove," Rosen said. One reason is because artificial intelligence systems are trained with large volumes of similar content, but in this case there was not enough because such attacks are rare.