We describe an application of inductive logic programming to transfer learning. Transfer learning is the use of knowledge learned in a source task to improve learning in a related target task. The tasks we work with are in reinforcement learning domains. Our approach transfers relational macros, which are finite-state machines in which the transition conditions and the node actions are represen...

Inductive k-independent graphs are a generalization of chordal graphs and have recently been advocated in the context of interference-avoiding wireless communication scheduling. The NP-hard problem of finding maximum-weight induced c-colorable subgraphs, which is a generalization of finding maximum independent sets, naturally occurs when selecting c sets of pairwise non-conflicting jobs (modele...

We present context-sensitive Multiple Task Learning, or csMTL as a method of inductive transfer embedded in the well known WEKA machine learning suite. csMTL uses a single output neural network and additional contextual inputs for learning multiple tasks. Inductive transfer occurs from secondary tasks to the model for the primary task so as to improve its predictive performance. The WEKA multi-...

In this paper, we discuss a mechanism for transfer learning in the context of inductive process modeling. We begin by describing the dual role of knowledge as a source of model components and structural constraints. Next, we review the task of inductive process modeling and emphasize the effect of domain knowledge on the learning component. We then describe the performance and learning elements...

Knowledge Acquisition is an important task when developing image interpretation systems. Whereas in the past this task has been done by interviewing an expert, the current trend is to collect large data bases of images associated with expert description ( known as picture archiving systems). This makes it possible to use inductive machine learning techniques for knowledge acquisition of image i...

csMTL, or context-sensitive Multiple Task Learning, is presented as a method of inductive transfer that uses a single output neural network and additional contextual inputs for learning multiple tasks. The csMTL approach is demonstrated to produce hypotheses that are equivalent to or better than standard MTL hypotheses when learning a primary task in the presence of related and unrelated tasks....

We give a formalism of arithmetic mixed sheaves, including the case of arithmetic mixed Hodge structures which are recently studied by P. Griffiths, M. Green [22], [23] and M. Asakura [1] using other methods. This notion became necessary for us to describe the image of Griffiths’ Abel-Jacobi map for a generic hypersurface (inspired by previous work of M. Green [21] and C. Voisin [45], [46]), an...