No abstract

We introduce a novel framework called "artificial physics", which provides distributed control of large collections of agents. The agents react to artificial forces that are motivated by natural physical laws. This framework provides an effective mechanism for achieving self-assembly, fault-tolerance, and self-repair. Examples are shown for various regular geometric configurations of agents. A further example demonstrates that self-assembly via distributed control can also perform distributed computation.

Abstract. In this introduction, we define the ~erm bias as it is used in machine learning systems. We motivate the importance of automated methods for evaluating and selecting biases using a framework of blas selection as search in bias and meta-bias spaces. Recent research in the field of machine Iearning bias is summarized.Keywords: bias, concept learning I n t r o d u c t i o nThis speciat issue of Machine Learning focuses on the evaluation and selection of biases. The papers in this issue describe methods by which intelligent systems automatically evaluate and select their own biases, and tools for analyzing and testing various approaches to bias selection. In this paper, we motivate the importance of this topic. Since most readers will be familiar with supervised concept learning, we phrase our discussion within that framework. However, bias as we present it here is a part of every type of learning.We outline a framework for treating bias selection as a process of designing appropriate search methods over the bias and meta-bias spaces. This framework has two essential features: it divides bias into representational and procedural components, and it characterizes learning as search within multiple tiers. The sources of bias within a system can thus be identified and analyzed with respect to their influence on this multi-tiered search process, and bias shift becomes search at the bias level. The framework provides an analytic tool with which to compare different systems (including those not developed within the framework), as weil as an abstract formalism and architecture to guide the development of new systems.We begin by defining what we mean by the term bias. Next, we explain why the selection and evaluation of biases is a critical task for intelligent systems. We then describe our search-based framework for bias selection. Finaily, we survey recent research in this field, using the concepts developed in out framework to guide the discussion.

No abstract

No abstract