We describe a reinforcement learning system that transfers relational skills from a previously learned source task to a related target task. The system uses inductive logic programming to analyze experience in the source task, and transfers rules about when to take actions. The target-task learner accepts these rules through an advice-taking algorithm. Our system also accepts humanprovided advi...

Regulation of central neurogenesis by a peripheral target has been previously demonstrated in the ventral nerve cord of the leech Hirudo medicinalis (Baptista, C. A., Gershon, T. R. and Macagno, E. R. (1990). Nature 346, 855-858) Specifically, innervation of the male genitalia by the fifth and sixth segmental ganglia (the sex ganglia) was shown to trigger the birth of several hundred central ne...

The semidian ( approximately 12 h) periodicity in the effect of far-red (FR) interruptions of the light period preceding inductive darkness on flowering in Pharbitis nil appears to be mediated by phytochrome: (a) promotion by interruptions 2 hours before inductive darkness (-2 hours) and inhibition at -8 hours are greater the higher the proportion of FR/R+FR during the interruption; (b) brief F...

A potential low magnetic moment standard reference material (SRM) was studied in an interlaboratory comparison. The mean and the standard deviation of the saturation moment m s, the remanent moment m r, and the intrinsic coercivity H c of nine samples were extracted from hysteresis-loop measurements. Samples were measured by thirteen laboratories using inductive-field loopers, vibrating-sample ...

This paper describes an application of an inductive learning techniques to case-based reasoning. We introduce two main forms of induction, define case-based reasoning and present a combination of both. The evaluation of the proposed system, called TA3, is carried out on a classification task, namely character recognition. We show how inductive knowledge improves knowledge representation and in ...

H(⊗1 C+) denotes the Hardy space of square integrable functions analytic in each variable separately. Let P be the natural projection of L(⊗1 C+) onto H(⊗1 C+). A Hankel operator with symbol b is the linear operator from H(⊗1 C+) to H(⊗1 C+) given by Hbφ = Pbφ. We show that ‖Hb‖ ≃ ‖Pb‖BMO(⊗n 1 C+), where the right hand norm is S.-Y. Chang and R. Fefferman product BMO. This fact has well known e...

A tradeoff exists between the range of learning tasks solved by an induction system, and its performance on those tasks. We propose dynamic-bias induction, an approach in which bias is dynamically constructed as a function of the learning task. This admits the possibility of a high performance inductive learner that applies to a wide range of learning tasks. We assess the benefits and limitatio...