We present the systematic method of Multitask Learning for incorporating prior knowledge (hints) into the inductive learning system of neural networks. Multitask Learning is an inductive transfer method which uses domain information about related tasks as inductive bias to guide the learning process towards better solutions of the main problem. These tasks are presented to the learning system i...

Inductive logic programming (ILP) is a research area which has its roots in inductive machine learning and computational logic. The paper gives an introduction to this area based on a distinction between two diierent semantics used in inductive logic programming, and illustrates their application in knowledge discovery and programming. Whereas most research in inductive logic programming has fo...

We show that the notion of bias in inductive concept learning can be quantified in a way that directly relates to learning performance, and that this quantitative theory of bias can provide guidance in the design of effective learning algorithms. We apply this idea by measuring some common language biases, including restriction to conjunctive concepts and conjunctive concepts with internal disj...

Random walks are at the heart of many existing deep learning algorithms for graph data. However, such algorithms have many limitations that arise from the use of random walks, e.g., the features resulting from these methods are unable to transfer to new nodes and graphs as they are tied to node identity. In this work, we introduce the notion of attributed random walks which serves as a basis fo...

We propose an interleaved inductive-abductive model for reasoning about complex spatio-temporal narratives. Typed Inductive Logic Programming (Typed-ILP) is used as a basis for learning the domain theory by generalising from observation data, whereas abductive reasoning is used for noisy data correction by scenario and narrative completion thereby improving the inductive learning to get semanti...

Machine Learning (ML) methods are very powerful tools to automate the knowledge acquisition (KA) task. Particularly, in ill-structured domains where there is no clear idea about which concepts exist, inductive unsupervised learning systems appear to be a promising approach to help experts in the early stages of the acquisition process. In this paper we examine the concept of inductive bias, whi...

We propose and study a new intelligent teaching paradigm called active teaching in this paper. In contrast to active learning, we assume that the learner can only passively conduct inductive learning from the given examples, but the teacher (oracle) can actively provide “good” examples to the learner, in order to speed up the teaching (learning) process. We establish the framework with four spe...

This paper approaches the importance of bias selection in the context of validating Knowledge Bases (KB) obtained by inductive learning systems. We propose a framework for automatic validation of induced KBs based on the capability of shifting the bias in the inductive learning system. We claim that this framework is useful not only when the system has to validate its own results, but also when...

In this paper we propose a distributed approach to the inductive learning problem and present an implementation of the Distributed Learning System (DLS). Our method involves breaking up the data set into different sub-samples, using an inductive learning program (in our case PLS1) for each sample, and finally synthesizing the results given by each program into a final concept by using a genetic...