tailieunhanh - Báo cáo khoa học: "FORUM ON CONNECTIONISM "

I will then pose some questions for the panel and the audience to discuss, if they are interested, and I will make a few critical comments on the abstracts submitted by Waltz and Sejnowski, intended to provoke responses from them. The situation is reminiscent of automata theory, where the basic metaphor of finite control, read/write head(s), input and output tape(s) has m a n y different variations. The general theory of connectionist machines seems to be at a relatively early stage, however. . | FORUM ON CONNECTIONISM Questions about Connectionist Models of Natural Language Mark Liberman AT T Bell Laboratories 600 Mountain Avenue Murray Hill NJ 07974 MODERATOR STATEMENT My role as interlocutor for this ACL Forum on Connec-tionism is to promote discussion by asking questions and making provocative comments. I will begin by asking some questions that I will attempt to answer myself in order to define some terms. I will then pose some questions for the panel and the audience to discuss if they are interested and I will make a few critical comments on the abstracts submitted by Waltz and Sejnowski intended to provoke responses from them. I. What is a connectionist model The basic metaphor involves a finite set of nodes interconnected by a finite set of directed arcs. Each node transmits on its output arcs some function of what it receives on its input arcs these transfer functions are usually described parametrically for instance in terms of a linear combination of the inputs composed with some nonlinear threshold-like function the transfer function may involve a random variable. A subset of the nodes or arcs are designated as inputs and or outputs whose values are supplied or used by the environment. Time is generally quantized and treated in an idealized way as if all connections involved a transmission delay exactly equal to the time quantum this is presumably done for convenience and tractability since neural systems are not like this. The nodes transfer function may contain some sort of memory . an activation level. The state of the network at time step t determines its state at time step t 1 at least probabilistically if random variables are involved the network calculates its response to a change in its input by executing a sequence of time-steps sufficient to permit information to propagate through the required number of nodes and to permit the system to attain at least approximately a fixed point that maps back into itself or into a state .