information or product described herein. Connection Machine ® is a registered trademark of Thinking Machines Corporation. CM, CM-1, CM-2, CM-200, CM-5, and DataVault are trademarks of Thinking Machines Corporation. CMosT and Prism are trademarks of Thinking Machines Corporation C * ® & is a registered

of the Connection Machine provides a platform for the implementation and evaluation of parallel learning techniques. The architecture of the Connection Machine is described along with limitations of the language interface that constrain the implementation of learning programs. Connection Machine implementations

We examine the possibility of applying massive parallelism to the powerful machine learning algorithm AQ developed at the University of Illinois. We show how one new tool, the Connection Machine, may be used to significantly speed up AO. We present complexity estimates of parallel source code

algorithm, error back-propagation, on a fine-grained parallel computer, the Connection Machine. As an example of how the system can be used, we present a parallel implementation of NETtalk, a connectionist network that learns the mapping from English text to the pronunciation of that text. Currently

F the use ot computers affects increasingly broader segments of computer systems increase steadily. For-tunately, the technology base for the last twenty years has continued to improve at a steady rate-increasing in capacity and speed while decreasing in cost for perfor-mance. However, the demands outpace the technology. This raises the question, can we make a quantum leap in perfor-mance while the rate of technology improvement remains relatively constant? Computer architects have followed two general approaches in response to this question. The first uses exotic technology in a fairly conventional serial computer architecture. This approach suffers from manufacturing and maintenance problems and high costs. The second approach exploits the parallelism inherent in many problems. The parallel approach seems to offer the best long-term strategy because, as the problems grow, more and more opportunities arise to exploit the parallel-ism inherent in the data itself. Where do we find the inherent parallel-ism and how do we exploit it? Most com-puter programs consist of a control sequence (the instructions) and a collection of data elements. Large programs have tens of thousands of instructions operat-

This paper describes an object recognition algorithm both on a sequential machine and on a SIMD parallel processor such as the MIT Connection Machine. The parallel version is shown to run three to four orders of magnitude faster than the sequential version. I.

Abstract: This paper describes a parallel real-time stereomatching algorithm and its implementation on the Connection MachineTM computing system. computer, a new massively parallel The main features of the algorithm are 1) real-time performance, 2) the full exploitation of the OP- 3) a

We give two parallel algorithms for sequence comparison on the Connection Machine 2 (CM-2). The specific comparison measure we compute is the erfif distance: given a finite alphabet £ and two input sequences X £ £ + and Y £ E + the edit distance Y) is the minimum cost of transforming X into Y via

This paper reports on a fast implementation of the three-dimensional nonadaptive Parallel Multipole Method (PMM) on the Connection Machine system model CM--2. The data interactions within the decomposition tree are modeled by a hierarchy of three dimensional grids forming a pyramid in which parent

Connection Machine Lisp is a dialect of Lisp extended to al-low a fine.grained, data-oriented style of parallel execution. We introduce a new data structure, the xapping, that is like a sparse array whose elements can be processed in parallel. This kind of processing is suitable for implementation