Diplomats from around the world met in Geneva last week for the United Nations' third Informal Expert Meeting on lethal autonomous weapons systems (LAWS), commonly dubbed "killer robots". Their aim was to make progress on deciding how, or if, LAWS should be regulated under international humanitarian law. A range of views were expressed at the meeting, from Pakistan being in favour of a full ban, to the UK favouring no new regulation for LAWS, and several positions in between. Despite the range of views on offer, there was some common ground. It is generally agreed that LAWS are governed by international humanitarian law.

When Hollywood actress Angelina Jolie found out she carried the BRCA1 gene, her doctors told her she had an 87% chance of developing breast cancer. Armed with this knowledge, she chose to undergo a double mastectomy in 2013 to reduce the risk to around 5%. This kind of genetic testing can now be done much faster and at lower cost, giving clinicians the ability to target treatments more effectively. And combining this technological breakthrough with cloud computing and artificial intelligence is giving pharmaceutical companies the tools to develop drugs faster and with greater chance of success. One beneficiary of this new approach is Eric Dishman, founder of tech giant Intel's first health research and innovation laboratory in 1999 and a founding member of its digital health group in 2005.

This paper presents a novel nonmyopic adaptive Gaussian process planning (GPP) framework endowed with a general class of Lipschitz continuous reward functions that can unify some active learning/sensing and Bayesian optimization criteria and offer practitioners some flexibility to specify their desired choices for defining new tasks/problems. In particular, it utilizes a principled Bayesian sequential decision problem framework for jointly and naturally optimizing the exploration-exploitation trade-off. In general, the resulting induced GPP policy cannot be derived exactly due to an uncountable set of candidate observations. A key contribution of our work here thus lies in exploiting the Lipschitz continuity of the reward functions to solve for a nonmyopic adaptive epsilon-optimal GPP (epsilon-GPP) policy. To plan in real time, we further propose an asymptotically optimal, branch-and-bound anytime variant of epsilon-GPP with performance guarantee. We empirically demonstrate the effectiveness of our epsilon-GPP policy and its anytime variant in Bayesian optimization and an energy harvesting task.

We consider the problem of modeling temporal textual data taking endogenous and exogenous processes into account. Such text documents arise in real world applications, including job advertisements and economic news articles, which are influenced by the fluctuations of the general economy. We propose a hierarchical Bayesian topic model which imposes a "group-correlated" hierarchical structure on the evolution of topics over time incorporating both processes, and show that this model can be estimated from Markov chain Monte Carlo sampling methods. We further demonstrate that this model captures the intrinsic relationships between the topic distribution and the time-dependent factors, and compare its performance with latent Dirichlet allocation (LDA) and two other related models. The model is applied to two collections of documents to illustrate its empirical performance: online job advertisements from DirectEmployers Association and journalists' postings on BusinessInsider.com.

The Augmented Lagragian Method (ALM) and Alternating Direction Method of Multiplier (ADMM) have been powerful optimization methods for general convex programming subject to linear constraint. We consider the convex problem whose objective consists of a smooth part and a nonsmooth but simple part. We propose the Fast Proximal Augmented Lagragian Method (Fast PALM) which achieves the convergence rate O(1/K2), compared with O(1/K) by the traditional PALM. In order to further reduce the per-iteration complexity and handle the multi-blocks problem, we propose the Fast Proximal ADMM with Parallel Splitting (Fast PL-ADMM-PS) method. It also partially improves the rate related to the smooth part of the objective function. Experimental results on both synthesized and real world data demonstrate that our fast methods significantly improve the previous PALM and ADMM

Methods for learning word representations using large text corpora have received much attention lately due to their impressive performancein numerous natural language processing (NLP) tasks such as, semantic similarity measurement, and word analogy detection.Despite their success, these data-driven word representation learning methods do not considerthe rich semantic relational structure between words in a co-occurring context. On the other hand, already much manual effort has gone into the construction of semantic lexicons such as the WordNetthat represent the meanings of words by defining the various relationships that exist among the words in a language.We consider the question, can we improve the word representations learnt using a corpora by integrating theknowledge from semantic lexicons?. For this purpose, we propose a joint word representation learning method that simultaneously predictsthe co-occurrences of two words in a sentence subject to the relational constrains given by the semantic lexicon.We use relations that exist between words in the lexicon to regularize the word representations learnt from the corpus.Our proposed method statistically significantly outperforms previously proposed methods for incorporating semantic lexicons into wordrepresentations on several benchmark datasets for semantic similarity and word analogy.

Solving a multi-objective constraint optimization problem (MO-COP) typically consists in computing all Pareto optimal solutions, which are exponentially many in the general case. This causes two problems: time complexity and lack of decisiveness. We present an approach which, given a number k of desired solutions, selects k Pareto optimal solutions that are representative of the Pareto front. We analyze the computational complexity of the underlying computational problem and provide exact and approximation procedures.

We introduce Scheduling MTL (SMTL) an extension of Metric Temporal Logic that supports the specification of complex scheduling problems with repeated and conditional occurrences of activities, and rich temporal relationships among them. We define the syntax and semantics of SMTL, and explore natural restrictions of the language to gain tractability. We also provide an algorithm for finding a schedule to a problem specified as an SMTL formula, and establish a novel equivalence between a fragment of MTL and simple temporal networks, a widely-used formalism in AI temporal planning.

Knowledge graph embedding refers to projecting entities and relations in knowledge graph into continuous vector spaces. Current state-of-the-art models are translation-based model, which build embeddings by treating relation as translation from head entity to tail entity. However, previous models is too strict to model the complex and diverse entities and relations(e.g. symmetric/transitive/one-to-many/many-to-many relations). To address these issues, we propose a new principle to allow flexible translation between entity and relation vectors. We can design a novel score function to favor flexible translation for each translation-based models without increasing model complexity. To evaluate the proposed principle, we incorporate it into previous method and conduct triple classification on benchmark datasets. Experimental results show that the principle can remarkably improve the performance compared with several state-of-the-art baselines.

We investigate case-based reasoning (CBR) problems where cases are represented by abstract factors and (positive or negative) outcomes, and an outcome for a new case, represented by abstract factors, needs to be established. To this end, we employ abstract argumentation (AA) and propose a novel methodology for CBR, called AA-CBR. The argumentative formulation naturally allows to characterise the computation of an outcome as a dialogical process between a proponent and an opponent, and can also be used to extract explanations for why an outcome for a new case is (not) computed.