Our goal is to identify beneficial interventions from observational data. We consider interventions that are narrowly focused (impacting few covariates) and may be tailored to each individual or globally enacted over a population. For applications where harmful intervention is drastically worse than proposing no change, we propose a conservative definition of the optimal intervention. Assuming the underlying relationship remains invariant under intervention, we develop efficient algorithms to identify the optimal intervention policy from limited data and provide theoretical guarantees for our approach in a Gaussian Process setting. Although our methods assume covariates can be precisely adjusted, they remain capable of improving outcomes in misspecified settings where interventions incur unintentional downstream effects. Empirically, our approach identifies good interventions in two practical applications: gene perturbation and writing improvement.

We consider the problem of strongly-convex online optimization in presence of adversarial delays; in a T-iteration online game, the feedback of the player's query at time t is arbitrarily delayed by an adversary for d_t rounds and delivered before the game ends, at iteration t+d_t-1. Specifically for \algo{online-gradient-descent} algorithm we show it has a simple regret bound of \Oh{\sum_{t=1}^T \log (1+ \frac{d_t}{t})}. This gives a clear and simple bound without resorting any distributional and limiting assumptions on the delays. We further show how this result encompasses and generalizes several of the existing known results in the literature. Specifically it matches the celebrated logarithmic regret \Oh{\log T} when there are no delays (i.e. d_t = 1) and regret bound of \Oh{\tau \log T} for constant delays d_t = \tau.

The field of Artificial Intelligence has made great strides forward recently, for example AlphaGo's recent victory against the world champion Lee Sedol in the game of Go, leading to great optimism about the field. But are we really moving towards smarter machines, or are these successes restricted to certain classes of problems, leaving other challenges untouched? In 2016, the Allen Institute for Artificial Intelligence (AI2) ran the Allen AI Science Challenge, a competition to test machines on an ostensibly difficult task, namely answering 8th Grade science questions. Our motivations were to encourage the field to set its sights broader and higher by exploring a problem that appears to require modeling, reasoning, language understanding, and commonsense knowledge, to probe the state of the art on this task, and sow the seeds for possible future breakthroughs. The challenge received a strong response, with 780 teams from all over the world participating.

Abstract--The current paper proposes a novel neural network model for recognizing visually perceived human actions. The proposed multiple spatiotemporal scales recurrent neural network (MSTRNN) model is derived by introducing multiple timescale recurrent dynamics to the conventional convolutional neural network model. One of the essential characteristics of the MSTRNN is that its architecture imposes both spatial and temporal constraints simultaneously on the neural activity which vary in multiple scales among different layers. As suggested by the principle of the upward and downward causation, it is assumed that the network can develop meaningful structures such as functional hierarchy by taking advantage of such constraints during the course of learning. T o evaluate the characteristics of the model, the current study uses three types of human action video dataset consisting of different types of primitive actions and different levels of compositionality on them. The performance of the MSTRNN in testing with these dataset is compared with the ones by other representative deep learning models used in the field. The analysis of the internal representation obtained through the learning with the dataset clarifies what sorts of functional hierarchy can be developed by extracting the essential compositionality underlying the dataset. ECENTL Y, a convolutional neural network (CNN) [1], inspired by a mammalian visual cortex, showed a remarkably better object image recognition performance than conventional vision recognition schemes which employ elaborately hand-coded visual features. A CNN trained with 1 million visual images from ImageNet [2] was able to classify hundreds of object images with an error rate of 6.67% [3], and demonstrated near-human performance [4]. As a consequence, CNNs are less effective in handling video image patterns than static images. To address this shortcoming, a number of action recognition models have been developed. H. Lee is with the Department of Electrical Engineering, Korea Institute of Science and Technology, Daejeon 305-701, Republic of Korea, email: (haanvidlee@gmail.com). M. Jung is with the Department of Electrical Engineering, Korea Institute of Science and Technology, Daejeon 305-701, Republic of Korea, email: (minju5436@gmail.com).

Amazon apparently won't be the only company offering drone delivery service: The United Postal Service could follow suit. UPS announced Tuesday it had successfully tested out a drone for residential delivery, a press release said. The company worked with Workhorse Group, a manufacturing company that created both the drone and the electric UPS car used to test the flight. The test drone successfully flew to its designated location, dropped off the package and then proceeded on its delivery route. The drone tested could carry up to 10 pounds.

It is an approach best summed up by Homer Simpson, who told his son Bart'If something is hard to do, then it's not worth doing'. Now, researchers say the view may actually be hardwired in our brains. They say it is so powerful, it can even change what we think we see to make the easier option more attractive. Researchers say the approach may actually be hardwired in our brains. They say it is so powerful, it can even change what we think we see to make the easier option more attractive.

Think that artificial intelligence isn't intelligent yet? Quick: What do you think of when you hear the words "artificial intelligence?" You might think of Siri or Alexa. Maybe you picture robots that are coming to steal your job. Or perhaps you think of technology that turns against its inventors and spells the end of the human race. Whatever your personal stance may be, according to recent headlines, the population is split when it comes to their belief in AI.

Researchers have developed a new interface that allows people with paralysis to communicate faster than ever through brain-controlled typing. The system uses tiny electrode implants, each roughly the size of a baby aspirin, to move an on-screen cursor when a person imagines their own hand movements. According to the Stanford-led team, the system marks a'major milestone' in efforts to improve life for those with severe limb weakness and paralysis, including people with ALS and spinal cord injuries. Researchers have developed a new interface that allows people with paralysis to communicate faster than ever through brain-controlled typing. In the new study, the Stanford-led team used an intracortical brain-computer interface called the BrainGate Neural Interface System.

Jonathan Lazar (jlazar@towson.edu) is a professor of computer and information sciences and director of the Undergraduate Program in Information Systems at Towson University, Towson, MD, and recipient of the SIGCHI 2016 Social Impact Award. Elizabeth Churchill (churchill@acm.org) is a director of user experience at Google, San Francisco, CA, and Secretary/Treasurer of ACM. Tovi Grossman (tovi.grossman@autodesk.com) is a distinguished research scientist in the User Interface Research Group at Autodesk Research, Toronto, Canada. Gerrit C. van der Veer (gerrit@acm.org) is an emeritus professor of multimedia and culture at the Vrije Universiteit Amsterdam, the Netherlands, guest professor of human-media interaction at Twente University, Twente, the Netherlands, of human-computer and society at the Dutch Open University, Heerlen, Netherlands, of interaction design at the Dalian Maritime University, Dalian, China, and of animation and multimedia at the Lushun Academy of Fine Arts, Shenyang, China. Philippe Palanque (palanque@irit.fr) is a professor of computer science at Université Paul Sabatier Paul Sabatier – Toulouse III, France, and head of the Interactive Critical Systems research group of the IRIT laboratory, Toulouse, France. John "Scooter" Morris (scooter@cgl.ucsf.edu) is an adjunct professor in the Department of Pharmaceutical Chemistry at the University of California San Francisco and executive director of the Resource for Biocomputing, Visualization and Informatics, a U.S. National Institutes of Health Biomedical Technology Research Resource at the University of California San Francisco. Jennifer Mankoff (mankoff@cs.cmu.edu) is a professor in the Human Computer Interaction Institute at Carnegie Mellon University, Pittsburgh, PA.

Peer review is the process by which experts in some discipline comment on the quality of the works of others in that discipline. Peer review of written works is firmly embedded in current academic research practice where it is positioned as the gateway process and quality control mechanism for submissions to conferences, journals, and funding bodies across a wide range of disciplines. It is probably safe to assume that peer review in some form will remain a cornerstone of academic practice for years to come, evidence-based criticisms of this process in computer science22,32,45 and other disciplines23,28 notwithstanding. While parts of the academic peer review process have been streamlined in the last few decades to take technological advances into account, there are many more opportunities for computational support that are not currently being exploited. The aim of this article is to identify such opportunities and describe a few early solutions for automating key stages in the established academic peer review process. When developing these solutions we have found it useful to build on our background in machine learning and artificial intelligence: in particular, we utilize a feature-based perspective in which the handcrafted features on which conventional peer review usually depends (for example, keywords) can be improved by feature weighting, selection, and construction (see Flach17 for a broader perspective on the role and importance of features in machine learning). Twenty-five years ago, at the start of our academic careers, submitting a paper to a conference was a fairly involved and time-consuming process that roughly went as follows: Once an author had produced the manuscript (in the original sense, that is, manually produced on a typewriter, possibly by someone from the university's pool of typists), he or she would make up to seven photocopies, stick all of them in a large envelope, and send them to the program chair of the conference, taking into account that international mail would take 3–5 days to arrive. On their end, the program chair would receive all those envelopes, allocate the papers to the various members of the program committee, and send them out for review by mail in another batch of big envelopes. Reviews would be completed by hand on paper and mailed back or brought to the program committee meeting. Finally, notifications and reviews would be sent back by the program chair to the authors by mail. Submissions to journals would follow a very similar process.