AI Opaqueness: What Makes AI Systems More Transparent?

Polymeric Gas Separation Membranes: What Makes them Industrially more Attractive?

Towards Transparent AI Systems: Interpreting Visual Question Answering Models

Deep neural networks have shown striking progress and obtained state-of-the-art results in many AI research fields in the recent years. However, it is often unsatisfying to not know why they predict what they do. In this paper, we address the problem of interpreting Visual Question Answering (VQA) models. Specifically, we are interested in finding what part of the input (pixels in images or wor...

What Is AI, Anyway?

In this article, the scientific and technological goals of artificial intelligence, and a proposal of ten fundamental problems in AI research are discussed This article is an introduction to Scientific DataLink’s microfiche publication of the Yale AI technical reports In this context, examples of research conducted at the Yale Artificial Intelligence Project relating to each of the research pro...

Transparent, explainable, and accountable AI for robotics

Recent governmental statements from the United States (USA) (1, 2), the European Union (EU) (3), and China (4) identify artificial intelligence (AI) and robotics as economic and policy priorities. Despite this enthusiasm, chal lenges remain. Systems can make unfair and discriminatory decisions, replicate or develop biases, and behave in inscrutable and unexpected ways in highly sensitive enviro...

Fuzzy Systems in AI

This paper reviews motivations for introducing fuzzy sets and fuzzy logic to knowledge representation in artificial intelligence. First we consider some areas of successful application of conventional approaches to system analysis. We then discuss limitations of these approaches and the reasons behind these limitations. We introduce different levels of representation for complex systems and dis...