Ute Schmid

Metaphors and heuristic-driven theory projection (HDTP)

A classical approach of modeling metaphoric expressions uses a source concept network that is mapped to a target concept network. Both networks are often represented as algebras. In this paper, a representation using the mathematically sound framework of heuristic-driven theory projection (HDTP) is presented which is--although quite different from classical approaches--algebraic in nature, too. HDTP has the advantage that a structural description of source and target can be given and the connection between both domains are more clearly specified. The major aspects of the formal properties of HDTP, the specification of the underlying algorithm HDTP-A, and the development of a formal semantics for analogical reasoning will be discussed. We will apply HDTP to different types of metaphors.

Inductive programming meets the real world

Inductive programming can liberate users from performing tedious and repetitive tasks.

Inductive rule learning on the knowledge level

We present an application of the analytical inductive programming system Igor to learning sets of recursive rules from positive experience. We propose that this approach can be used within cognitive architectures to model regularity detection and generalization learning. Induced recursive rule sets represent the knowledge which can produce systematic and productive behavior in complex situations - that is, control knowledge for chaining actions in different, but structural similar situations. We argue, that an analytical approach which is governed by regularity detection in example experience is more plausible than generate-and-test approaches. After introducing analytical inductive programming with Igor we will give a variety of example applications from different problem solving domains. Furthermore, we demonstrate that the same generalization mechanism can be applied to rule acquisition for reasoning and natural language processing.

The challenge of complexity for cognitive systems

Complex cognition addresses research on (a) high-level cognitive processes - mainly problem solving, reasoning, and decision making - and their interaction with more basic processes such as perception, learning, motivation and emotion and (b) cognitive processes which take place in a complex, typically dynamic, environment. Our focus is on AI systems and cognitive models dealing with complexity and on psychological findings which can inspire or challenge cognitive systems research. In this overview we first motivate why we have to go beyond models for rather simple cognitive processes and reductionist experiments. Afterwards, we give a characterization of complexity from our perspective. We introduce the triad of cognitive science methods - analytical, empirical, and engineering methods - which in our opinion have all to be utilized to tackle complex cognition. Afterwards we highlight three aspects of complex cognition - complex problem solving, dynamic decision making, and learning of concepts, skills and strategies. We conclude with some reflections about and challenges for future research.

Analysis and Evaluation of Inductive Programming Systems in a Higher-Order Framework

In this paper we present a comparison of several inductive programming (IP) systems. IP addresses the problem of learning (recursive) programs from incomplete specifications, such as input/output examples. First, we introduce conditional higher-order term rewriting as a common framework for inductive program synthesis. Then we characterise the ILP system Golem and the inductive functional system MagicHaskeller within this framework. In consequence, we propose the inductive functional system Igor II as a powerful and efficient approach to IP. Performance of all systems on a representative set of sample problems is evaluated and shows the strength of Igor II.

An introduction to inductive programming

The research field of inductive programming is concerned with the design of algorithms for learning computer programs with complex flow of control (typically recursive calls) from incomplete specifications such as examples. We introduce a basic algorithmic approach for inductive programming and illustrate it with three systems: dialogs learns logic programs by combining inductive and abductive reasoning; the classical thesys system and its extension igor1 learn functional programs based on a recurrence detection mechanism in traces; igor2 learns functional programs over algebraic data-types making use of constructor-term rewriting systems. Furthermore, we give a short history of inductive programming, discuss related approaches, and give hints about current applications and possible future directions of research.

Inference and Visualization of Spatial Relations

We present an approach to spatial inference which is based on the procedural semantics of spatial relations. In contrast to qualitative reasoning, we do not use discrete symbolic models. Instead, relations between pairs of objects are represented by parameterized homogeneous transformation matrices with numerical constraints. A textual description of a spatial scene is transformed into a graph with objects and annotated local reference systems as nodes and relations as arcs. Inference is realized by multiplication of transformation matrices, constraint propagation and verification. Constraints consisting of equations and inequations containing trigonometric functions can be solved using machine learning techniques. By assigning values to the parameters and using heuristics for the placement of objects, a visualization of the described spatial layout can be generated from the graph.

Approaches and Applications of Inductive Programming

This report documents the program and the outcomes of Dagstuhl Seminar 13502 “Approaches and Applications of Inductive Programming”. After a short introduction to inductive programming research, an overview of the talks and the outcomes of discussion groups is given.

Can Machine Intelligence be Measured in the Same Way as Human intelligence

In recent years the number of research projects on computer programs solving human intelligence problems in artificial intelligence (AI), artificial general intelligence, as well as in Cognitive Modelling, has significantly grown. One reason could be the interest of such problems as benchmarks for AI algorithms. Another, more fundamental, motivation behind this area of research might be the (implicit) assumption that a computer program that successfully can solve human intelligence problems has human-level intelligence and vice versa. This paper analyses this assumption.

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.