Michael Siebers

Computer models solving intelligence test problems

While some computational models of intelligence test problems were proposed throughout the second half of the XXth century, in the first years of the XXIst century we have seen an increasing number of computer systems being able to score well on particular intelligence test tasks. However, despite this increasing trend there has been no general account of all these works in terms of how they relate to each other and what their real achievements are. Also, there is poor understanding about what intelligence tests measure in machines, whether they are useful to evaluate AI systems, whether they are really challenging problems, and whether they are useful to understand (human) intelligence. In this paper, we provide some insight on these issues, in the form of nine specific questions, by giving a comprehensive account of about thirty computer models, from the 1960s to nowadays, and their relationships, focussing on the range of intelligence test tasks they address, the purpose of the models, how general or specialised these models are, the AI techniques they use in each case, their comparison with human performance, and their evaluation of item difficulty. As a conclusion, these tests and the computer models attempting them show that AI is still lacking general techniques to deal with a variety of problems at the same time. Nonetheless, a renewed attention on these problems and a more careful understanding of what intelligence tests offer for AI may help build new bridges between psychometrics, cognitive science, and AI; and may motivate new kinds of problem repositories.

Semi-analytic natural number series induction

The induction of natural number series is a prototypical intelligence test task. We present a system which solves this task semi-analytically. As first step the term structure defining a given number series is guessed. Then the semi-instantiated formula is used to abduct new number series examples which can be solved more easily.

Problems of video-based pain detection in patients with dementia: a road map to an interdisciplinary solution

BackgroundGiven the unreliable self-report in patients with dementia, pain assessment should also rely on the observation of pain behaviors, such as facial expressions. Ideal observers should be well trained and should observe the patient continuously in order to pick up any pain-indicative behavior; which are requisitions beyond realistic possibilities of pain care. Therefore, the need for video-based pain detection systems has been repeatedly voiced. Such systems would allow for constant monitoring of pain behaviors and thereby allow for a timely adjustment of pain management in these fragile patients, who are often undertreated for pain.MethodsIn this road map paper we describe an interdisciplinary approach to develop such a video-based pain detection system. The development starts with the selection of appropriate video material of people in pain as well as the development of technical methods to capture their faces. Furthermore, single facial motions are automatically extracted according to an international coding system. Computer algorithms are trained to detect the combination and timing of those motions, which are pain-indicative.Results/conclusionWe hope to encourage colleagues to join forces and to inform end-users about an imminent solution of a pressing pain-care problem. For the near future, implementation of such systems can be foreseen to monitor immobile patients in intensive and postoperative care situations.

Explaining Black-Box Classifiers with ILP - Empowering LIME with Aleph to Approximate Non-linear Decisions with Relational Rules.

We propose an adaption of the explanation-generating system LIME. While LIME relies on sparse linear models, we explore how richer explanations can be generated. As application domain we use images which consist of a coarse representation of ancient graves. The graves are divided into two classes and can be characterised by meaningful features and relations. This domain was generated in analogy to a classic concept acquisition domain researched in psychology. Like LIME, our approach draws samples around a simplified representation of the instance to be explained. The samples are labelled by a generator – simulating a black-box classifier trained on the images. In contrast to LIME, we feed this information to the ILP system Aleph. We customised Aleph’s evaluation function to take into account the similarity of instances. We applied our approach to generate explanations for different variants of the ancient graves domain. We show that our explanations can involve richer knowledge thereby going beyond the expressiveness of sparse linear models.

Was the Year 2000 a Leap Year? Step-Wise Narrowing Theories with Metagol

Many people believe that every fourth year is a leap year. However, this rule is too general: year X is a leap year if X is divisible by 4 except if X is divisible by 100 except if X is divisible by 400. We call such a theory with alternating generalisation and specialisation a step-wise narrowed theory. We present and evaluate an extension to the ILP system Metagol which facilitates learning such theories. We enabled Metagol to learn over-general theories by allowing a limited number of false positives during learning. This variant is iteratively applied on a learning task. For each iteration after the first, positive examples are the false positives from the previous iteration and negative examples are the true positives from the previous iteration. Iteration continues until no more false positives are present. Then, the theories are combined to a single step-wise narrowed theory. We evaluate the usefulness of our approach in the leap year domain. We can show that our approach finds solutions with fewer clauses, higher accuracy, and in shorter time.

Intentional Forgetting in Artificial Intelligence Systems: Perspectives and Challenges.

Current trends, like digital transformation and ubiquitous computing, yield in massive increase in available data and information. In artificial intelligence (AI) systems, capacity of knowledge bases is limited due to computational complexity of many inference algorithms. Consequently, continuously sampling information and unfiltered storing in knowledge bases does not seem to be a promising or even feasible strategy. In human evolution, learning and forgetting have evolved as advantageous strategies for coping with available information by adding new knowledge to and removing irrelevant information from the human memory. Learning has been adopted in AI systems in various algorithms and applications. Forgetting, however, especially intentional forgetting, has not been sufficiently considered, yet. Thus, the objective of this paper is to discuss intentional forgetting in the context of AI systems as a first step. Starting with the new priority research program on ‘Intentional Forgetting’ (DFG-SPP 1921), definitions and interpretations of intentional forgetting in AI systems from different perspectives (knowledge representation, cognition, ontologies, reasoning, machine learning, self-organization, and distributed AI) are presented and opportunities as well as challenges are derived.

Transfer of Domain Knowledge in Plan Generation: Learning Goal-dependent Annulling Conditions for Actions

In this paper we present an approach to avoid dead-ends during automated plan generation. A first-order logic formula can be learned that holds in a state if the application of a specific action will lead to a dead-end. Starting from small problems within a problem domain examples of states where the application of the action will lead to a dead-end will be collected. The states will be generalized using inductive logic programming to a first-order logic formula. We will show how different notions of goal-dependence could be integrated in this approach. The formula learned will be used to speed-up automated plan generation. Furthermore, it provides insight into the planning domain under consideration.