DARPA (Defense Advanced Research Projects Agency), is a division of the American Defense Department that investigates new technologies. It has for some time regarded the current generation of AI technologies as important in the future. It has been in the forefront of AI research in image recognition, speech recognition and generation, robotics, autonomous vehicles, medical diagnostic systems, and more. However, DARPA is well aware that despite the high level of problem-solving capabilities of AI programs – they lack explainability. AI deep learning algorithms use complex mathematics that is very difficult for human users to understand or comprehend.

The field of natural language processing (NLP) makes it possible to understand patterns in large amounts of language data, from online reviews to audio recordings. But before a data scientist can really dig into an NLP problem, he or she must lay the groundwork that helps a model make sense of the different units of language it will encounter. Word embeddings are a set of feature engineering techniques widely used in predictive NLP modeling, particularly in deep learning applications. Word embeddings transform sparse vector representations of words into a dense, continuous vector space, enabling you to identify similarities between words and phrases -- on a large scale -- based on their context. In this piece, I'll explain the reasoning behind word embeddings and demostrate how to use these techniques to create clusters of similar words using data from 500,000 Amazon reviews of food. You can download the dataset to follow along.

Imagine working at Facebook and being the person/people who added Stories to the social network after seeing the way they took off on Snapchat and Instagram. Then think about the fact that hardly anyone is using the feature. That probably explains the reasoning behind opening the section up to Pages. Yep, #brands are getting access to the evaporating, 24-hour shelf-life videos now, too. Maybe Facebook found a group that will actually use them?

Towards Artificial Argumentation

The field of computational models of argument is emerging as an important aspect of artificial intelligence research. The reason for this is based on the recognition that if we are to develop robust intelligent systems, then it is imperative that they can handle incomplete and inconsistent information in a way that somehow emulates the way humans tackle such a complex task. And one of the key ways that humans do this is to use argumentation either internally, by evaluating arguments and counterarguments‚ or externally, by for instance entering into a discussion or debate where arguments are exchanged. As we report in this review, recent developments in the field are leading to technology for artificial argumentation, in the legal, medical, and e-government domains, and interesting tools for argument mining, for debating technologies, and for argumentation solvers are emerging.

The General Data Protection Regulation (GDPR) is a wide-ranging and complex regulation intended to strengthen and unify data protection for all individuals within the European Union (EU). A year ago I blogged about the data governance ramifications of GDPR, and in this blog I'll focus on another facet of GDPR to talk about a related analytics topic: explainable artificial intelligence (AI). First, let's start with GDPR. Article 22 of GDPR, "Automated individual decision-making, including profiling," concerns the use of data in decision-making that affects individuals, such as a person applying for a loan. The data subject shall have the right not to be subject to a decision based solely on automated processing, including profiling, which produces legal effects concerning him or her or similarly significantly affects him or her." Point 2 of Article 22 describes exclusions (including situations involving the person's explicit consent, such as applying for a loan), but the key issue for our discussion here is in point 3: "…the data controller shall implement suitable measures to safeguard the data subject's rights and freedoms and legitimate interests, at least the right to obtain human intervention on the part of the controller, to express his or her point of view and to contest the decision."

Different agents may have different points of view. Following a popular approach in the artificial intelligence literature, this can be modelled by means of different abstract argumentation frameworks, each consisting of a set of arguments the agent is contemplating and a binary attack-relation between them. A question arising in this context is whether the diversity of views observed in such a profile of argumentation frameworks is consistent with the assumption that every individual argumentation framework is induced by a combination of, first, some basic factual attack-relation between the arguments and, second, the personal preferences of the agent concerned regarding the moral or social values the arguments under scrutiny relate to. We treat this question of rationalisability of a profile as an algorithmic problem and identify tractable and intractable cases. In doing so, we distinguish different constraints on admissible rationalisations, e.g., concerning the types of preferences used or the number of distinct values involved. We also distinguish two different semantics for rationalisability, which differ in the assumptions made on how agents treat attacks between arguments they do not report. This research agenda, bringing together ideas from abstract argumentation and social choice, is useful for understanding what types of profiles can reasonably be expected to occur in a multiagent system.

Over the last 12 months or so there's been incredible excitement about artificial intelligence and all of the amazing things it can do for us--everything from driving cars to making pizza (super-cool video!). But -- and this is a big "but" -- artificial intelligence comes with many challenges, including trying to decipher what these models have learned, and thus their decision criteria. In my last post, I discussed how regulations such as Europe's General Data Protection Regulation will demand Explainable AI. This is a field of science that attempts to remove the black box and deliver AI performance while also providing an explanation as to the "how" and "why" a model derives its decisions. FICO has been pioneering Explainable AI for over 25 years; one of our recent Explainable AI patent filings replaced a patent awarded back in 1998.

Argumentation is an active area of modern artificial intelligence (AI) research, with connections to a range of fields, from computational complexity theory and knowledge representation and reasoning to philosophy and social sciences, as well as application-oriented work in domains such as legal reasoning, multi-agent systems, and decision support. Argumentation frameworks (AFs) of abstract argumentation have become the graph-based formal model of choice for many approaches to argumentation in AI, with semantics defining sets of jointly acceptable arguments, i.e., extensions. Understanding the dynamics of AFs has been recently recognized as an important topic in the study of argumentation in AI. In this work, we focus on the so-called extension enforcement problem in abstract argumentation as a recently proposed form of argumentation dynamics. We provide a nearly complete computational complexity map of argument-fixed extension enforcement under various major AF semantics, with results ranging from polynomial-time algorithms to completeness for the second level of the polynomial hierarchy. Complementing the complexity results, we propose algorithms for NP-hard extension enforcement based on constraint optimization under the maximum satisfiability (MaxSAT) paradigm. Going beyond NP, we propose novel MaxSAT-based counterexample-guided abstraction refinement procedures for the second-level complete problems and present empirical results on a prototype system constituting the first approach to extension enforcement in its generality.

The answer to questions of trust and bias in AI is largely seen in the focus on Explainable AI. Although traditionally viewed as "black boxes", AI and machine learning systems are not ontologically inscrutable.