This paper presents a novel algorithm for learning in a class of stochastic Markov decision processes (MDPs) with continuous state and action spaces that trades speed for accuracy. A transform of the stochastic MDP into a deterministic one is presented…

Organizations must establish processes for managing knowledge across boundaries because of the specialized and task-dependent forms of knowledge required to deliver products and services. To address this challenge an integrative framework is developed that identifies and integrates the value of…

Much Learning is done by way of studying precedents and exercises. A teacher supplies a story, gives a problem, and expects a student both to solve a problem and to discover a principle. The student must find the correspondence between…

There are many situations in which a very detailed low-level description encodes, through a hierarchical organization, a recognizable higher-order pattern. The macro-molecular structural conformations of proteins exhibit higher order regularities whose recognition is complicated by many factors. ARIADNE searches for…

We had previously shown that regularization principles lead to approximation schemes, as Radial Basis Functions, which are equivalent to networks with one layer of hidden units, called Regularization Networks. In this paper we show that regularization networks encompass a much…

What are the characteristics of the process by which an intent is transformed into a plan and then a program? How is a program debugged? This paper analyzes these questions in the context of understanding simple turtle programs. To understand…

Organizations must establish processes for managing knowledge across boundaries because of the specialized and task-dependent forms of knowledge required to deliver products and services. To address this challenge an integrative framework is developed that identifies and integrates the value of…

This paper investigates the potential for a carbon tax to induce R&D, and for the consequent induced technical change (ITC) to lower the macroeconomic cost of abating carbon emissions. ITC is modelled within a general equilibrium simulation of the U.S.…

The goal of the work reported here is to capture the commonsense knowledge of non-expert human contributors. Achieving this goal will enable more intelligent human-computer interfaces and pave the way for computers to reason about our world. In the domain…

The thesis explores a puzzle in technological capability development: many firms in China follow the "normal" way of technological capability development suggested by the existing literature but have not made much progress, while some firms that deviate from the "normal"…