Statistical machine learning is widely used in image classification. However, most techniques (1) require many images to achieve high accuracy and (2) do not provide support for reasoning below the level of classification, and so are unable to support secondary reasoning, such as the existence and position of light sources and other objects outside the image. This paper describes an Inductive Logic Programming approach called Logical Vision which overcomes some of these limitations. LV uses Meta-Interpretive Learning (MIL) combined with low-level extraction of high-contrast points sampled from the image to learn recursive logic programs describing the image. In published work LV was demonstrated capable of high-accuracy prediction of classes such as regular polygon from small numbers of images where Support Vector Machines and Convolutional Neural Networks gave near random predictions in some cases. LV has so far only been applied to noise-free, artificially generated images. This paper extends LV by (a) addressing classification noise using a new noise-telerant version of the MIL system Metagol, (b) addressing attribute noise using primitive-level statistical estimators to identify sub-objects in real images, (c) using a wider class of background models representing classical 2D shapes such as circles and ellipses, (d) providing richer learnable background knowledge in the form of a simple but generic recursive theory of light reflection. In our experiments we consider noisy images in both natural science settings and in a RoboCup competition setting. The natural science settings involve identification of the position of the light source in telescopic and microscopic images, while the RoboCup setting involves identification of the position of the ball. Our results indicate that with real images the new noise-robust version of LV using a single example (i.e. one-shot LV) converges to an accuracy at least comparable to a thirty-shot statistical machine learner on both prediction of hidden light sources in the scientific settings and in the RoboCup setting. Moreover, we demonstrate that a general background recursive theory of light can itself be invented using LV and used to identify ambiguities in the convexity/concavity of objects such as craters in the scientific setting and partial obscuration of the ball in the RoboCup setting.

During the 1980s Michie defined Machine Learning in terms of two orthogonal axes of performance: predictive accuracy and comprehensibility of generated hypotheses. Since predictive accuracy was readily measurable and comprehensibility not so, later definitions in the 1990s, such as Mitchell’s, tended to use a one-dimensional approach to Machine Learning based solely on predictive accuracy, ultimately favouring statistical over symbolic Machine Learning approaches. In this paper we provide a definition of comprehensibility of hypotheses which can be estimated using human participant trials. We present two sets of experiments testing human comprehensibility of logic programs. In the first experiment we test human comprehensibility with and without predicate invention. Results indicate comprehensibility is affected not only by the complexity of the presented program but also by the existence of anonymous predicate symbols. In the second experiment we directly test whether any state-of-the-art ILP systems are ultra-strong learners in Michie’s sense, and select the Metagol system for use in humans trials. Results show participants were not able to learn the relational concept on their own from a set of examples but they were able to apply the relational definition provided by the ILP system correctly. This implies the existence of a class of relational concepts which are hard to acquire for humans, though easy to understand given an abstract explanation. We believe improved understanding of this class could have potential relevance to contexts involving human learning, teaching and verbal interaction.

Machine Learning has been used to automatically generate a probabilistic food-web from Farm Scale Evaluation (FSE) data. The initial food web proposed by machine learning has been examined by domain experts and comparison with the literature shows that many of the links are corroborated. The FSE data were collected using two different sampling techniques, namely Vortis and pitfall. The corroboration of the initial Vortis food web, generated by machine learning, was performed manually by the domain experts. However, manual corroboration of hypothetical trophic links is difficult and requires significant amounts of time. In this paper we review the method and the main results on machine learning of trophic links. We study common trophic links from Vortis and pitfall data. We also describe a new method and present initial results on automatic corroboration of trophic links using text mining.

This paper describes the use of a mixture of abduction and induction for the temporal modeling of the effects of toxins in metabolic networks. Background knowledge is used which describes network topology and functional classes of enzymes. This background knowledge, which represents the present state of understanding, is incomplete. In order to overcome this incompleteness hypotheses are considered which consist of a mixture of specific inhibitions of enzymes (ground facts) together with general (non-ground) rules which predict classes of enzymes likely to be inhibited by the toxin. The foreground examples were derived from in vivo experiments involving NMR analysis of time-varying metabolite concentrations in rat urine following injections of toxin. Hypotheses about inhibition are built using the inductive logic programming system Progol5.0 and predictive accuracy is assessed for both the ground and the non-ground cases.