Results 1 
5 of
5
Theories for Mutagenicity: A Study in FirstOrder and FeatureBased Induction
 Artificial Intelligence
, 1996
"... A classic problem from chemistry is used to test a conjecture that in domains for which data are most naturally represented by graphs, theories constructed with Inductive Logic Programming (ILP) will significantly outperform those using simpler featurebased methods. One area that has long been asso ..."
Abstract

Cited by 150 (30 self)
 Add to MetaCart
A classic problem from chemistry is used to test a conjecture that in domains for which data are most naturally represented by graphs, theories constructed with Inductive Logic Programming (ILP) will significantly outperform those using simpler featurebased methods. One area that has long been associated with graphbased or structural representation and reasoning is organic chemistry. In this field, we consider the problem of predicting the mutagenic activity of small molecules: a property that is related to carcinogenicity, and an important consideration in developing less hazardous drugs. By providing an ILP system with progressively more structural information concerning the molecules, we compare the predictive power of the logical theories constructed against benchmarks set by regression, neural, and treebased methods. 1 Introduction Constructing theories to explain observations occupies much of the creative hours of scientists and engineers. Programs from the field of Inductiv...
Terminal attractor algorithms: A critical analysis
 Neurocomputing
, 1997
"... One of the fundamental drawbacks of learning by gradient descent techniques is the susceptibility to local minima during training. Recently, some authors have independently introduced new learning algorithms that are based on the properties of terminal attractors and repellers. These algorithms were ..."
Abstract

Cited by 4 (2 self)
 Add to MetaCart
One of the fundamental drawbacks of learning by gradient descent techniques is the susceptibility to local minima during training. Recently, some authors have independently introduced new learning algorithms that are based on the properties of terminal attractors and repellers. These algorithms were claimed to perform global optimization of the cost in finite time, provided that a null solution exists. In this paper, we prove that, in the case of local minima free error functions, terminal attractor algorithms guarantee that the optimal solution is reached in a number of steps that is independent of the cost function. Moreover, in the case of multimodal functions, we prove that, unfortunately, there are no theoretical guarantees that a global solution can be reached or that the algorithms perform satisfactorily from an operational point of view, unless particular favourable conditions are satisfied. On the other hand, the ideas behind these innovative methods are very interesting and d...
Biochemical knowledge discovery using Inductive Logic Programming
, 1998
"... Machine Learning algorithms are being increasingly used for knowledge discovery tasks. Approaches can be broadly divided by distinguishing discovery of procedural from that of declarative knowledge. Client requirements determine which of these is appropriate. This paper discusses an experimental ..."
Abstract
 Add to MetaCart
Machine Learning algorithms are being increasingly used for knowledge discovery tasks. Approaches can be broadly divided by distinguishing discovery of procedural from that of declarative knowledge. Client requirements determine which of these is appropriate. This paper discusses an experimental application of machine learning in an area related to drug design. The bottleneck here is in finding appropriate constraints to reduce the large number of candidate molecules to be synthesised and tested. Such constraints can be viewed as declarative specifications of the structural elements necessary for high medicinal activity and low toxicity. The firstorder representation used within Inductive Logic Programming (ILP) provides an appropriate description language for such constraints. Within this application area knowledge accreditation requires not only a demonstration of predictive accuracy but also, and crucially, a certification of novel insight into the structural chemistry. This paper describes an experiment in which the ILP system Progol was used to obtain structural constraints associated with mutagenicity of molecules. In doing so Progol found a new indicator of mutagenicity within a subset of previously published data. This subset was already known not to be amenable to statistical regression, though its complement was adequately explained by a linear model. According to the combined accuracy/explanation criterion provided in this paper, on both subsets comparative trials show that Progol's structurallyoriented hypotheses are preferable to those of other machine learning algorithms. ? The results in this paper are published separately in [7, 16] 1
Chapter 1
"... The objective of this research is to develop new learning methods based upon optimization techniques. Two different but related areas are focused on. The first is to develop new learning algorithms for neural networks. These new learning techniques could later be used in a variety of applications su ..."
Abstract
 Add to MetaCart
The objective of this research is to develop new learning methods based upon optimization techniques. Two different but related areas are focused on. The first is to develop new learning algorithms for neural networks. These new learning techniques could later be used in a variety of applications such as control and pattern