UK Prime Minister Theresa May has announced plans to invest in a "whole new industry around AI in healthcare". Researchers at the University of Southern California have developed a new predictive model for heart disease, which makes use of a smartphone app. Machine-learning techniques are poised to hit the mainstream over the next few years. Machine learning has long been touted as the next big thing for healthcare. With countless startups investing in that promise, applications are emerging across everything from diagnostics to drug discovery.

We propose to take a novel approach to robot system design where each building block of a larger system is represented as a differentiable program, i.e. a deep neural network. This representation allows for integrating algorithmic planning and deep learning in a principled manner, and thus combine the benefits of model-free and model-based methods. We apply the proposed approach to a challenging partially observable robot navigation task. The robot must navigate to a goal in a previously unseen 3-D environment without knowing its initial location, and instead relying on a 2-D floor map and visual observations from an onboard camera. We introduce the Navigation Networks (NavNets) that encode state estimation, planning and acting in a single, end-to-end trainable recurrent neural network. In preliminary simulation experiments we successfully trained navigation networks to solve the challenging partially observable navigation task.

The user uses the control panel (A) to specify the detail information to visualize (e.g., level of detail, rule filters). The rule-based explanatory representation is visualized as a matrix (B), where each row represents a rule, and each column is a feature used in the rules. The user can also filter the data or use a customized input in the data filter (C) and navigate the filtered dataset in the data table (D). Abstract--With the growing adoption of machine learning techniques, there is a surge of research interest towards making machine learning systems more transparent and interpretable. Various visualizations have been developed to help model developers understand, diagnose, and refine machine learning models. However, a large number of potential but neglected users are the domain experts with little knowledge of machine learning but are expected to work with machine learning systems. In this paper, we present an interactive visualization technique to help users with little ...

Score following is the process of tracking a musical performance (audio) with respect to a known symbolic representation (a score). We start this paper by formulating score following as a multimodal Markov Decision Process, the mathematical foundation for sequential decision making. Given this formal definition, we address the score following task with state-of-the-art deep reinforcement learning (RL) algorithms such as synchronous advantage actor critic (A2C). In particular, we design multimodal RL agents that simultaneously learn to listen to music, read the scores from images of sheet music, and follow the audio along in the sheet, in an end-to-end fashion. All this behavior is learned entirely from scratch, based on a weak and potentially delayed reward signal that indicates to the agent how close it is to the correct position in the score. Besides discussing the theoretical advantages of this learning paradigm, we show in experiments that it is in fact superior compared to previously proposed methods for score following in raw sheet music images.

Text statistics Number of figures: 6 Number of supplementary figures: 14 Number of words in abstract: 139 Abstract Searching for a target object in a cluttered scene constitutes a fundamental challenge in daily vision. Visual search must be selective enough to discriminate the target from distractors, invariant to changes in the appearance of the target, efficient to avoid exhaustive exploration of the image, and must generalize to locate novel target objects with zero-shot training. Previous work has focused on searching for perfect matches of a target after extensive category-specific training. Here we show for the first time that humans can efficiently and invariantly search for natural objects in complex scenes. To gain insight into the mechanisms that guide visual search, we propose a biologically inspired computational model that can locate targets without exhaustive sampling and generalize to novel objects. The model provides an approximation to the mechanisms integrating ...

This paper addresses the semantics of weighted argumentation graphs that are bipolar, i.e. contain both attacks and supports for arguments. We build on previous work by Amgoud, Ben-Naim et. al. We study the various characteristics of acceptability semantics that have been introduced in these works. We provide a simplified and mathematically elegant formulation of these characteristics. The formulation is modular because it cleanly separates aggregation of attacking and supporting arguments (for a given argument a) from the computation of their influence on a's initial weight. We discuss various semantics for bipolar argumentation graphs in the light of these characteristics. Based on the modular framework, we prove general convergence and divergence theorems. We show that all semantics converge for all acyclic graphs and that no sum-based semantics can converge for all graphs. In particular, we show divergence of Euler-based semantics for certain cyclic graphs. We also provide the first semantics for bipolar weighted graphs that converges for all graphs.

Repeated game has long been the touchstone model for agents' long-run relationships. Previous results suggest that it is particularly difficult for a repeated game player to exert an autocratic control on the payoffs since they are jointly determined by all participants. This work discovers that the scale of a player's capability to unilaterally influence the payoffs may have been much underestimated. Under the conventional iterated prisoner's dilemma, we develop a general framework for controlling the feasible region where the players' payoff pairs lie. A control strategy player is able to confine the payoff pairs in her objective region, as long as this region has feasible linear boundaries. With this framework, many well-known existing strategies can be categorized and various new strategies with nice properties can be further identified. We show that the control strategies perform well either in a tournament or against a human-like opponent.

The detection of software vulnerabilities (or vulnerabilities for short) is an important problem that has yet to be tackled, as manifested by many vulnerabilities reported on a daily basis. This calls for machine learning methods to automate vulnerability detection. Deep learning is attractive for this purpose because it does not require human experts to manually define features. Despite the tremendous success of deep learning in other domains, its applicability to vulnerability detection is not systematically understood. In order to fill this void, we propose the first systematic framework for using deep learning to detect vulnerabilities. The framework, dubbed Syntax-based, Semantics-based, and Vector Representations (SySeVR), focuses on obtaining program representations that can accommodate syntax and semantic information pertinent to vulnerabilities. Our experiments with 4 software products demonstrate the usefulness of the framework: we detect 15 vulnerabilities that are not reported in the National Vulnerability Database. Among these 15 vulnerabilities, 7 are unknown and have been reported to the vendors, and the other 8 have been "silently" patched by the vendors when releasing newer versions of the products.

We found an easy and quick post-learning method named "Icing on the Cake" to enhance a classification performance in deep learning. The method is that we train only the final classifier again after an ordinary training is done.

MDPs extended with LTLf/LDLf non-Markovian rewards have recently attracted interest as a way to specify rewards declaratively. In this paper, we discuss how a reinforcement learning agent can learn policies fulfilling LTLf/LDLf goals. In particular we focus on the case where we have two separate representations of the world: one for the agent, using the (predefined, possibly low-level) features available to it, and one for the goal, expressed in terms of high-level (human-understandable) fluents. We formally define the problem and show how it can be solved. Moreover, we provide experimental evidence that keeping the RL agent feature space separated from the goal's can work in practice, showing interesting cases where the agent can indeed learn a policy that fulfills the LTLf/LDLf goal using only its features (augmented with additional memory).