Ford Motor Co. is investing $1 billion in a months-old startup founded by two pioneers in the nascent autonomous vehicle sector. The Pittsburgh-based artificial intelligence company Argo AI will develop the brains -- specifically, a virtual driver system -- for the fully autonomous vehicles Ford has promised to bring to market in 2021. Founders Bryan Salesky and Peter Rander are former leaders of the self-driving car teams at Uber Technologies Inc. and Alphabet Inc.'s Google. "This is a unique partnership," Mark Fields, Ford's chief executive officer, said in an interview. "A lot of tech companies are looking for customers and a lot of OEMs are looking for technology partners. We are getting expertise, and Argo AI is getting a customer in Ford."

Automation is happening, and will change the daily work activities of everyone, from miners and landscapers to commercial bankers, fashion designers, welders, and CEOs. Use the interactive to explore how robotics and artificial intelligence could potentially change how work is done in four settings: oil and gas exploration, aircraft maintenance, hospital emergency departments, and grocery stores. These case studies are not precise projections. The vision of the future they provide is based on the hypotheses of industry experts. To learn more about the impact of automation on the global economy and labor markets, read the McKinsey Global Institute research report Harnessing automation for a future that works.

Are you familiar with self-driving cars? These things would not be possible without the help of Machine Learning--the study of pattern recognition and prediction within the field of computer science. This course is taught by Stanford-educated, Silicon Valley experts that have decades of direct experience under their belts. They will teach you, in the simplest way possible (and with major visual techniques), to put Machine Learning and Python into action. With these skills under your belt, your programming skills will take a whole new level of power.

Online learning with streaming data in a distributed and collaborative manner can be useful in a wide range of applications. This topic has been receiving considerable attention in recent years with emphasis on both single-task and multitask scenarios. In single-task adaptation, agents cooperate to track an objective of common interest, while in multitask adaptation agents track multiple objectives simultaneously. Regularization is one useful technique to promote and exploit similarity among tasks in the latter scenario. This work examines an alternative way to model relations among tasks by assuming that they all share a common latent feature representation. As a result, a new multitask learning formulation is presented and algorithms are developed for its solution in a distributed online manner. We present a unified framework to analyze the mean-square-error performance of the adaptive strategies, and conduct simulations to illustrate the theoretical findings and potential applications.

The cross-entropy loss commonly used in deep learning is closely related to the defining properties of optimal representations, but does not enforce some of the key properties. We show that this can be solved by adding a regularization term, which is in turn related to injecting multiplicative noise in the activations of a Deep Neural Network, a special case of which is the common practice of dropout. We show that our regularized loss function can be efficiently minimized using Information Dropout, a generalization of dropout rooted in information theoretic principles that automatically adapts to the data and can better exploit architectures of limited capacity. When the task is the reconstruction of the input, we show that our loss function yields a Variational Autoencoder as a special case, thus providing a link between representation learning, information theory and variational inference. Finally, we prove that we can promote the creation of disentangled representations simply by enforcing a factorized prior, a fact that has been observed empirically in recent work. Our experiments validate the theoretical intuitions behind our method, and we find that information dropout achieves a comparable or better generalization performance than binary dropout, especially on smaller models, since it can automatically adapt the noise to the structure of the network, as well as to the test sample.

The use of convex regularizers allows for easy optimization, though they often produce biased estimation and inferior prediction performance. Recently, nonconvex regularizers have attracted a lot of attention and outperformed convex ones. However, the resultant optimization problem is much harder. In this paper, for a large class of nonconvex regularizers, we propose to move the nonconvexity from the regularizer to the loss. The nonconvex regularizer is then transformed to a familiar convex regularizer, while the resultant loss function can still be guaranteed to be smooth. Learning with the convexified regularizer can be performed by existing efficient algorithms originally designed for convex regularizers (such as the proximal algorithm, Frank-Wolfe algorithm, alternating direction method of multipliers and stochastic gradient descent). Extensions are made when the convexified regularizer does not have closed-form proximal step, and when the loss function is nonconvex, nonsmooth. Extensive experiments on a variety of machine learning application scenarios show that optimizing the transformed problem is much faster than running the state-of-the-art on the original problem.

A cluster tree provides a highly-interpretable summary of a density function by representing the hierarchy of its high-density clusters. It is estimated using the empirical tree, which is the cluster tree constructed from a density estimator. This paper addresses the basic question of quantifying our uncertainty by assessing the statistical significance of topological features of an empirical cluster tree. We first study a variety of metrics that can be used to compare different trees, analyze their properties and assess their suitability for inference. We then propose methods to construct and summarize confidence sets for the unknown true cluster tree. We introduce a partial ordering on cluster trees which we use to prune some of the statistically insignificant features of the empirical tree, yielding interpretable and parsimonious cluster trees. Finally, we illustrate the proposed methods on a variety of synthetic examples and furthermore demonstrate their utility in the analysis of a Graft-versus-Host Disease (GvHD) data set.

The stochastic multi-armed bandit is a classical and well-studied model for characterizing the explorationexploitation tradeoff in various decision-making problems in stochastic settings. The most well-known objective in the multi-armed bandit model is to maximize the cumulative gain (or equivalently, to minimize the cumulative regret) that the agent achieves. Another line of research, called the pure exploration multi-armed bandit problem, which is motivated by a variety of practical applications including medical trials [Rob85, AB10], communication network [AB10], and crowdsourcing [ZCL14, CLTL15], has also attracted significant attention recently. In the pure exploration problem, the agent draws samples from the arms adaptively (the exploration phase), and finally commits to one of the feasible solutions specified by the problem. In a sense, the exploitation phase in the pure exploration problem simply consists of exploiting the solution to which the agent commits indefinitely. Therefore, the agent's objective is to identify the optimal (or near-optimal) feasible solution with high probability. In this paper, we focus on the problem of identifying the top-k arms (i.e., the k arms with the largest means) in a stochastic multi-armed bandit model. The problem is known as the Best-k-Arm problem, and has been extensively studied in the past decade [KS10, GGL12, GGLB11, KTAS12, BWV12, KK13, ZCL14, KCG15, SJR16]. We formally define the Best-k-Arm problem as follows.

ABSTRACT In this paper we describe approaches for discovering acoustic concepts and relations in text. The first major goal is to be able to identify text phrases which contain a notion of audibility and can be termed as a sound or an acoustic concept. We also propose a method to define an acoustic scene through a set of sound concepts. We use pattern matching and parts of speech tags to generate sound concepts from large scale text corpora. We use dependency parsing and LSTM recurrent neural network to predict a set of sound concepts for a given acoustic scene. These methods are not only helpful in creating an acoustic knowledge base but in the future can also directly help acoustic event and scene detection research. Index Terms-- Sound Concepts, Audio Events and Scenes, Acoustic Relations, Sound and Language 1. INTRODUCTION Analyzing non-speech content has been gaining a lot of attention in the audio community.

On the Web, there is always a need to aggregate opinions from the crowd (as in posts, social networks, forums, etc.). Different mechanisms have been implemented to capture these opinions such as "Like" in Facebook, "Favorite" in Twitter, thumbs-up/down, flagging, and so on. However, in more contested domains (e.g. Wikipedia, political discussion, and climate change discussion) these mechanisms are not sufficient since they only deal with each issue independently without considering the relationships between different claims. We can view a set of conflicting arguments as a graph in which the nodes represent arguments and the arcs between these nodes represent the defeat relation. A group of people can then collectively evaluate such graphs. To do this, the group must use a rule to aggregate their individual opinions about the entire argument graph. Here, we present the first experimental evaluation of different principles commonly employed by aggregation rules presented in the literature. We use randomized controlled experiments to investigate which principles people consider better at aggregating opinions under different conditions. Our analysis reveals a number of factors, not captured by traditional formal models, that play an important role in determining the efficacy of aggregation. These results help bring formal models of argumentation closer to real-world application.