We introduce neural networks for end-to-end differentiable proving of queries to knowledge bases by operating on dense vector representations of symbols. These neural networks are constructed recursively by taking inspiration from the backward chaining algorithm as used in Prolog. Specifically, we replace symbolic unification with a differentiable computation on vector representations of symbols using a radial basis function kernel, thereby combining symbolic reasoning with learning subsymbolic vector representations. By using gradient descent, the resulting neural network can be trained to infer facts from a given incomplete knowledge base. It learns to (i) place representations of similar symbols in close proximity in a vector space, (ii) make use of such similarities to prove queries, (iii) induce logical rules, and (iv) use provided and induced logical rules for multi-hop reasoning. We demonstrate that this architecture outperforms ComplEx, a state-of-the-art neural link prediction model, on three out of four benchmark knowledge bases while at the same time inducing interpretable function-free first-order logic rules.

Monsanto has sued Arkansas over dicamba bans in that state, but a court battle doesn't appear likely in North Dakota. The company says it prefers to work with states and will urge North Dakota officials to be flexible on the cutoff date if conditions warrant.

Quantitative CBA is a postprocessing algorithm for association rule classification algorithm CBA (Liu et al, 1998). QCBA uses original, undiscretized numerical attributes to optimize the discovered association rules, refining the boundaries of literals in the antecedent of the rules produced by CBA. Some rules as well as literals from the rules can consequently be removed, which makes the resulting classifier smaller. One-rule classification and crisp rules make CBA classification models possibly most comprehensible among all association rule classification algorithms. These viable properties are retained by QCBA. The postprocessing is conceptually fast, because it is performed on a relatively small number of rules that passed data coverage pruning in CBA. Benchmark of our QCBA approach on 22 UCI datasets shows average 53% decrease in the total size of the model as measured by the total number of conditions in all rules. Model accuracy remains on the same level as for CBA.

We study the problem of learning probabilistic first-order logical rules for knowledge base reasoning. This learning problem is difficult because it requires learning the parameters in a continuous space as well as the structure in a discrete space. We propose a framework, Neural Logic Programming, that combines the parameter and structure learning of first-order logical rules in an end-to-end differentiable model. This approach is inspired by a recently-developed differentiable logic called TensorLog [5], where inference tasks can be compiled into sequences of differentiable operations. We design a neural controller system that learns to compose these operations. Empirically, our method outperforms prior work on multiple knowledge base benchmark datasets, including Freebase and WikiMovies.

Machine Learning, thinking systems, expert systems, knowledge engineering, decision systems, neural networks - all synonymous loosely woven words in the evolving fabric of Artificial Intelligence. Of these Machine Learning (ML) and Artificial Intelligence (AI) are often debated and used interchangeably. In very abstract terms, ML is a structured approach for deriving meaningful predictions/insights from both structured and unstructured data. ML methods employ complex algorithms that enable analytics based on data, history and patterns. The field of data science continues to scale new heights enabled by the exponential growth in computing power over the last decade.

Keeping up with the speed at which data is generated on a daily basis and our need to extract insight from that data requires powerful and innovative technology that can understand what is contained in information beyond keyword matching. Thousands of claims, customer queries and large amounts of diverse data make the insurance industry a natural use case for artificial intelligence and cognitive technologies. A recent study from Tata Consultancy Services reported that the insurance sector has invested $124 million in AI, compared to an average of $70 million invested by other industries. From customer service to claims processing, AI is frequently cited as a disruptive force in the insurance sector. In this post, we will look at some of the most common applications of of AI in the insurance industry.

Transparency, user trust, and human comprehension are popular ethical motivations for interpretable machine learning. In support of these goals, researchers evaluate model explanation performance using humans and real world applications. This alone presents a challenge in many areas of artificial intelligence. In this position paper, we propose a distinction between descriptive and persuasive explanations. We discuss reasoning suggesting that functional interpretability may be correlated with cognitive function and user preferences. If this is indeed the case, evaluation and optimization using functional metrics could perpetuate implicit cognitive bias in explanations that threaten transparency. Finally, we propose two potential research directions to disambiguate cognitive function and explanation models, retaining control over the tradeoff between accuracy and interpretability.

Automated knowledge base construction is a long-standing challenge in AI. The goal is to abstract concise representations from various sources of knowledge, such as unstructured documents, web data and knowledge bases. The outcome is a knowledge graph that can be used to enhance downstream applications like search engines and business analytics. Highly accurate and extensive knowledge graphs are the prerequisite to enable machine reasoning and decision making in AI. For example, knowledge base construction was an essential component of the DeepQA system that defeated the human grand-champions at Jeopardy! and has since been a very active research direction as it enables the adaptation of AI solutions to new domains.

We used redescription mining to find interpretable rules revealing associations between those determinants that provide insights about the Alzheimer's disease (AD). We extended the CLUS-RM redescription mining algorithm to a constraint-based redescription mining (CBRM) setting, which enables several modes of targeted exploration of specific, user-constrained associations. Redescription mining enabled finding specific constructs of clinical and biological attributes that describe many groups of subjects of different size, homogeneity and levels of cognitive impairment. We confirmed some previously known findings. However, in some instances, as with the attributes: testosterone, the imaging attribute Spatial Pattern of Abnormalities for Recognition of Early AD, as well as the levels of leptin and angiopoietin-2 in plasma, we corroborated previously debatable findings or provided additional information about these variables and their association with AD pathogenesis. Applying redescription mining on ADNI data resulted with the discovery of one largely unknown attribute: the Pregnancy-Associated Protein-A (PAPP-A), which we found highly associated with cognitive impairment in AD. Statistically significant correlations (p <= 0.01) were found between PAPP-A and various different clinical tests. The high importance of this finding lies in the fact that PAPP-A is a metalloproteinase, known to cleave insulin-like growth factor binding proteins. Since it also shares similar substrates with A Disintegrin and the Metalloproteinase family of enzymes that act as {\alpha}-secretase to physiologically cleave amyloid precursor protein (APP) in the non-amyloidogenic pathway, it could be directly involved in the metabolism of APP very early during the disease course. Therefore, further studies should investigate the role of PAPP-A in the development of AD more thoroughly.

THAT a computer program can repeatedly beat the world champion at Go, a complex board game, is a coup for the fast-moving field of artificial intelligence (AI). Another high-stakes game, however, is taking place behind the scenes, as firms compete to hire the smartest AI experts. Technology giants, including Google, Facebook, Microsoft and Baidu, are racing to expand their AI activities. Last year they spent some $8.5 billion on deals, says Quid, a data firm. That was four times more than in 2010.