Replatforming a business of our size and scale takes time. However, our pace of innovation is accelerating. We're increasingly using structured data and artificial intelligence to transform shopping on eBay, delivering more personalization capabilities, continuing to iterate our mobile experience, and bringing more unique inventory and categories to our customers. We've got more work to do, but I'm confident we're on the right path. Now, let me turn it over to Scott, and he'll provide more details on our Q3 results.

In a major breakthrough in the field of speech recognition, Microsoft researchers have created a technology that accurately recognises the words in a conversation like humans do. The team from Microsoft Artificial Intelligence and Research reported a speech recognition system that makes the same or fewer errors than professional transcriptionists. The researchers reported a word error rate (WER) of 5.9 per cent, down from the 6.3 per cent WER the team reported just last month. The 5.9 per cent error rate is about equal to that of people who were asked to transcribe the same conversation, and it's the lowest ever recorded against the industry standard "Switchboard" speech recognition task. This is an historic achievement," said Xuedong Huang, the company's chief speech scientist in a Microsoft blog post. The milestone means that, for the first time, a computer can recognise the words in a conversation as well as a person would. In doing so, the team has beat a goal they set less than a year ago -- and greatly exceeded everyone else's expectations as well. "Even five years ago, I wouldn't have thought we could have achieved this.

Elon Musk is really accelerating the potential timeline for delivering self-driving: The Tesla CEO said on a press call that he hopes to deliver a test ride of fully autonomous Tesla vehicle driving by next year. Not a trip around the block, but a coast-to-coast road trip, he says. "Our goal is, and I feel pretty good about this goal, that we'll be able to do a demonstration drive of full autonomy all the way from LA to New York, from home in LA to let's say dropping you off in Time Square in New York, and then having the car go park itself, by the end of next year," he said on a press call today. To put that kind of accomplishment in perspective, current autonomous testing generally doesn't even cross state lines, let alone the country. It's a huge goal, and one that will potentially be replicable by every car Tesla makes between now and then, according to the new hardware and vehicle system updates Musk also announced today.

Image Forensics has already achieved great results for the source camera identification task on images. Standard approaches for data coming from Social Network Platforms cannot be applied due to different processes involved (e.g., scaling, compression, etc.). Over 1 billion images are shared each day on the Internet and obtaining information about their history from the moment they were acquired could be exploited for investigation purposes. In this paper, a classification engine for the reconstruction of the history of an image, is presented. Specifically, exploiting K-NN and decision trees classifiers and a-priori knowledge acquired through image analysis, we propose an automatic approach that can understand which Social Network Platform has processed an image and the software application used to perform the image upload. The engine makes use of proper alterations introduced by each platform as features. Results, in terms of global accuracy on a dataset of 2720 images, confirm the effectiveness of the proposed strategy.

In this work we extend to the interval-valued setting the notion of an overlap functions and we discuss a method which makes use of interval-valued overlap functions for constructing OWA operators with interval-valued weights. . Some properties of intervalvalued overlap functions and the derived interval-valued OWA operators are analysed. We specially focus on the homogeneity and migrativity properties. Keywords Interval-valued fuzzy sets interval-valued overlap functions Interval-valued overlap OWA operators interval weighted vector migrativity homogeneity 1 Introduction Interval-valued fuzzy sets [62] have been succesfully applied in many different problems. Just to mention some of the most recent ones, interval-valued fuzzy sets have been used in decision making(see, e.g., theworksbyKhalilandHassan[36]andChengetal. They have also been the origin of rich theoretical studies, as, for instance, the works by Bedregal et al. [3, 7], Dimuro et al. [28], Reiser et al. [48] and the recent works by Zywica et al. [64] and Takác [55]. From the point of view of applications, interval-valued fuzzy sets are a suitable tool to represent uncertain or incomplete information. In particular, the length of the intervalvalued membership degree of a given element can be understood as a measure of the lack of certainty of the expert for providing an exact membership value to that element [44].

Structural equation models (SEMs) and vector autoregressive models (VARMs) are two broad families of approaches that have been shown useful in effective brain connectivity studies. While VARMs postulate that a given region of interest in the brain is directionally connected to another one by virtue of time-lagged influences, SEMs assert that causal dependencies arise due to contemporaneous effects, and may even be adopted when nodal measurements are not necessarily multivariate time series. To unify these complementary perspectives, linear structural vector autoregressive models (SVARMs) that leverage both contemporaneous and time-lagged nodal data have recently been put forth. Albeit simple and tractable, linear SVARMs are quite limited since they are incapable of modeling nonlinear dependencies between neuronal time series. To this end, the overarching goal of the present paper is to considerably broaden the span of linear SVARMs by capturing nonlinearities through kernels, which have recently emerged as a powerful nonlinear modeling framework in canonical machine learning tasks, e.g., regression, classification, and dimensionality reduction. The merits of kernel-based methods are extended here to the task of learning the effective brain connectivity, and an efficient regularized estimator is put forth to leverage the edge sparsity inherent to real-world complex networks. Judicious kernel choice from a preselected dictionary of kernels is also addressed using a data-driven approach. Extensive numerical tests on ECoG data captured through a study on epileptic seizures demonstrate that it is possible to unveil previously unknown causal links between brain regions of interest.

In this paper, we consider linear state-space models with compressible innovations and convergent transition matrices in order to model spatiotemporally sparse transient events. We perform parameter and state estimation using a dynamic compressed sensing framework and develop an efficient solution consisting of two nested Expectation-Maximization (EM) algorithms. Under suitable sparsity assumptions on the innovations, we prove recovery guarantees and derive confidence bounds for the state estimates. We provide simulation studies as well as application to spike deconvolution from calcium imaging data which verify our theoretical results and show significant improvement over existing algorithms.

Body-worn video (BWV) cameras are increasingly utilized by police departments to provide a record of police-public interactions. However, large-scale BWV deployment produces terabytes of data per week, necessitating the development of effective computational methods to identify salient changes in video. In work carried out at the 2016 RIPS program at IPAM, UCLA, we present a novel two-stage framework for video change-point detection. First, we employ state-of-the-art machine learning methods including convolutional neural networks and support vector machines for scene classification. We then develop and compare change-point detection algorithms utilizing mean squared-error minimization, forecasting methods, hidden Markov models, and maximum likelihood estimation to identify noteworthy changes. We test our framework on detection of vehicle exits and entrances in a BWV data set provided by the Los Angeles Police Department and achieve over 90% recall and nearly 70% precision -- demonstrating robustness to rapid scene changes, extreme luminance differences, and frequent camera occlusions.

Abstract--The ability of a human being to extrapolate previously gained knowledge to other domains inspired a new family of methods in machine learning called transfer learning. Transfer learning is often based on the assumption that objects in both target and source domains share some common feature and/or data space. In this paper, we propose a simple and intuitive approach that minimizes iteratively the distance between source and target task distributions by optimizing the kernel target alignment (KT A). We show that this procedure is suitable for transfer learning by relating it to Hilbert-Schmidt Independence Criterion (HSIC) and Quadratic Mutual Information (QMI) maximization. We run our method on benchmark computer vision data sets and show that it can outperform some state-of-art methods. I NTRODUCTION Most research in machine learning is usually concentrated around the setting where a classifier is trained and tested on data drawn from the same distribution. This scenario has already been well investigated and in some tasks supervised approaches have almost no room for improvement. However, building humanlike intelligent systems requires them to be able to generalize the discovered patterns to previously unseen domains.

During the last decades more and more textual data have become available, creating a growing need to statistically analyze large amounts of textual data. The hugely popular Latent Dirichlet Allocation (LDA) model introduced by Blei et al. (2003) is a generative probability model where each document is summarized by a set of latent semantic themes, often called topics; formally, a topic is a probability distribution over the vocabulary. An estimated LDA model is therefore a compressed latent representation of the documents. LDA is a mixed membership model where each document is a mixture of topics, where each word (token) in a document belongs to a single topic. The basic LDA model is unsupervised, i.e. the topics are learned solely from the words in the documents without access to document labels. In many situations there are also other information we would like to incorporate in modeling a corpus of documents. A common example is when we have labeled documents, such as ratings of movies together with a movie description, illness category in medical journals or the location of the identified bug together with bug reports. In these situation, one can use a so called supervised topic model to find the semantic structure in the documents that are related to the class of interest. One of the first approaches to supervised topic models was proposed by Mcauliffe and Blei (2008).