Recurrent neural networks (RNNs) process input text sequentially and model the conditional transition between word tokens. In contrast, the advantages of recursive networks include that they explicitly model the compositionality and the recursive structure of natural language. However, the current recursive architecture is limited by its dependence on syntactic tree. In this paper, we introduce a robust syntactic parsing-independent tree structured model, Neural Tree Indexers (NTI) that provides a middle ground between the sequential RNNs and the syntactic treebased recursive models. NTI constructs a full n-ary tree by processing the input text with its node function in a bottom-up fashion. Attention mechanism can then be applied to both structure and node function. We implemented and evaluated a binarytree model of NTI, showing the model achieved the state-of-the-art performance on three different NLP tasks: natural language inference, answer sentence selection, and sentence classification, outperforming state-of-the-art recurrent and recursive neural networks.

In order for autonomous robots to operate in unstructured environments, several perceptual capabilities are required. Most of these skills cannot be hard-coded in the system beforehand, but need to be developed and learned over time as the agent explores and acquires novel experience. As a prototypical example of this setting, in this work we consider the task of visual object recognition in robotics: Images depicting different objects are received one frame at a time, and the system needs to incrementally update the internal model of known objects as new examples are gathered. In the last few years, machine learning has achieved remarkable results in a variety of applications for robotics and computer vision [1], [2], [3]. However, most of these methods have been developed for off-line (or "batch") settings, where the entire training set is available beforehand. The problem of updating a learned model online has been addressed in the literature [4], [5], [6], [7], but most algorithms proposed in this context do not take into account challenges that are characteristic of realistic lifelong learning applications. Specifically, in online classification settings, a major challenge is to cope with the situation in which a novel class is added to the model. Indeed, 1) most learning algorithms require the number of classes to be known beforehand and not grow indefinitely, and 2) the imbalance between the few examples of the new class (potentially just one) and the many examples of previously learned classes can lead to unexpected and undesired behaviors [8].

Bribery in elections is an important problem in computational social choice theory. However, bribery with money is often illegal in elections. Motivated by this, we introduce the notion of frugal bribery and formulate two new pertinent computational problems which we call Frugal-bribery and Frugal- $bribery to capture bribery without money in elections. In the proposed model, the briber is frugal in nature and this is captured by her inability to bribe votes of a certain kind, namely, non-vulnerable votes. In the Frugal-bribery problem, the goal is to make a certain candidate win the election by changing only vulnerable votes. In the Frugal-{dollar}bribery problem, the vulnerable votes have prices and the goal is to make a certain candidate win the election by changing only vulnerable votes, subject to a budget constraint of the briber. We further formulate two natural variants of the Frugal-{dollar}bribery problem namely Uniform-frugal-{dollar}bribery and Nonuniform-frugal-{dollar}bribery where the prices of the vulnerable votes are, respectively, all the same or different. We study the computational complexity of the above problems for unweighted and weighted elections for several commonly used voting rules. We observe that, even if we have only a small number of candidates, the problems are intractable for all voting rules studied here for weighted elections, with the sole exception of the Frugal-bribery problem for the plurality voting rule. In contrast, we have polynomial time algorithms for the Frugal-bribery problem for plurality, veto, k-approval, k-veto, and plurality with runoff voting rules for unweighted elections. However, the Frugal-{dollar}bribery problem is intractable for all the voting rules studied here barring the plurality and the veto voting rules for unweighted elections.

This is a hard topic to cover. I know a number of journalists and appreciate their work in communicating these advances to a wide audience. It's a hard job to convey complex concepts and in many cases they're not at fault for how it becomes warped by the broader community. Sadly, regardless of the exact way these research stories are warped, most AI and ML stories in the media will result in an audibly groan from researchers. As a researcher in the rapidly progressing field of machine learning, I see no need to fictionalize the tremendous advances we see.

The word "Disagree" is seen on the hand of Julia Grabowski during a town hall meeting for Republican U.S. Senator Bill Cassidy in Metairie, Louisiana. News about President Donald Trump -- including an apparently neglected vegetable garden that once belonged to former first lady Michelle Obama -- is inescapable. As The New York Times' Farhad Manjoo wrote, "he is no longer just the message. In many cases, he has become the medium." Mental health professionals in the U.S. have reported that the all-encompassing coverage of the president has induced anxiety and depression, or post-election stress, in many of their patients.

Volvo's Pilot Assist II in the 2017 S90 combines adaptive cruise control and lane-keeping assist for semi-autonomous driving. Fully autonomous cars are coming, but concerns ranging from regulatory issues to the handoff between machines and humans need to be addressed before drivers can let go of the wheel – and trust the technology. In the meantime, we'll likely be stuck in a middle ground of semi-autonomy between Level 2 and Level 3 over the next few years. Systems such as Tesla Autopilot, Mercedes-Benz Steering Assist and Volvo Pilot Assist II can take over part if not most of the driving task but still require human supervision – and a certain level of trust on the part of the driver. In the case of the Mercedes Steering Assist and Volvo Pilot Assist II, occasional driver intervention is required, otherwise the system deactivates.

LONDON – Guided by cameras and radars, and negotiating traffic and roundabouts, a self-driving Nissan car took to the streets of London on Monday for the Japanese company's first European tests of an autonomous vehicle. Traveling at up to 50 mph (80 kph) and moving from local streets to a major multilane road, the modified Nissan LEAF electric car showcased the kind of technology many hope to be the future of travel. Britain has been wooing developers of autonomous vehicles, hoping to grab a slice of an industry it estimates could be worth £900 billion ($1.1 trillion) worldwide by 2025. It also recently announced changes to allow for a single insurance policy to cover motorists driving conventionally and in autonomous mode, as it tries to get regulations in place to encourage the uptake of driverless cars from 2020. Britain's flexible approach to testing autonomous vehicles helped Nissan pick London for its first European tests, the director of its research center in Silicon Valley told Reuters. "It's not everywhere in Europe that we can go and drive on the road," Maarten Sierhuis said.

Machine Learning and AI are fast becoming ubiquitous in data driven businesses, that is to say, an awful lot of businesses. Here I choose a few areas where it's possible that big corporations haven't already eaten everybody's lunch. It's not uncharted territory -- if I could think of the next killer application, I'd be trying to do it! So-called after the California Gold Rush where the purveyors of picks and shovels made a killing (whereas the outcome for prospectors was mixed), the picks and shovels of machine intelligence are hardware, data feeds,and (arguably) the algorithms themselves. But these processors were designed for graphics.

Oxford University researchers have estimated that 47 percent of U.S. jobs could be automated within the next two decades. But which ones will robots take first? First, we should define "robots" (for this article only) as technologies, such as machine learning algorithms running on purpose-built computer platforms, that have been trained to perform tasks that currently require humans to perform. With this in mind, let's think about what you'll do after white-collar work. Oh, and I do have a solution for the short term that will make you the last to lose your job to a robot, but I'm saving it for the end of the article.

Their publications are highly respected within the research community, and span a myriad of topics such as Deep Reinforcement Learning, Bayesian Neural Nets, Robotics, transfer learning, and others. Being London-based, they recruit heavily from Oxford and Cambridge, which are great ML feeder programs in Europe. They hire an intellectually diverse team to focus on general AI research, including traditional software engineers to build infrastructure and tooling, UX designers to help make research tools, and even ecologists (Drew Purves) to research far-field ideas like the relationship between ecology and intelligence.