We consider a 2-layer, 3-node, n-input neural network whose nodes compute linear threshold functions of their inputs. We show that it is NPcomplete to decide whether there exist weights and thresholds for the three nodes of this network so that it will produce output consistent witha given set of training examples. We extend the result to other simple networks. This result suggests that those looking for perfect training algorithms cannot escape inherent computational difficulties just by considering only simple or very regular networks. It also suggests the importance, given a training problem, of finding an appropriate network and input encoding for that problem. It is left as an open problem to extend our result to nodes with nonlinear functions such as sigmoids.

A nonlinearity is required before matched filtering in mInimum error receivers when additive noise is present which is impulsive and highly non-Gaussian. Experiments were performed to determine whether the correct clipping nonlinearity could be provided by a single-input singleoutput multi-layerperceptron trained with back propagation. It was found that a multi-layer perceptron with one input and output node, 20 nodes in the first hidden layer, and 5 nodes in the second hidden layer could be trained to provide a clipping nonlinearity with fewer than 5,000 presentations of noiseless and corrupted waveform samples. A network trained at a relatively high signal-to-noise (SIN) ratio and then used as a front end for a linear matched filter detector greatly reduced the probability of error. The clipping nonlinearity formed by this network was similar to that used in current receivers designed for impulsive noise and provided similar substantial improvements in performance.

Jim Saveland For a fire in that fuel complex to Research Forester The Phoenix project ("Trial by Fire: grow to the size indicated in the time Associate Editor, AI Application in Understanding the Design Requirements indicated would require a midflame Natural Resource Management for Agents in Complex Environments." Agriculture 3) presents very interesting work in The authors go on to state, "Firefighting Forest Service forest fire simulation. I am especially objects are also accurately Southern Forest Fire Laboratory glad to see recognition that the "realtime, simulated; for example, bulldozers Route 1, Box 182A spatially distributed, multiagent, move at a maximum speed of... 0.5 Dry Branch, GA 31020 dynamic, and unpredictable fire kph when cutting a fireline." In reality, environment" provides an excellent sustained fireline production for Editor: opportunity to explore a variety of AI bulldozers is variable (0.1 - 2.0 kph) issues, such as how complex environments depending on steepness of the slope, Mr. Saveland's letter focuses our constrain the design of intelligent vegetation, and size of the bulldozer. I hope more AI researchers Furthermore, although bulldozers are between accuracy and realism.

The designer's input can be manually added to Design Automation: Automated Full-which itself is awkward) in the The author is criticizing the capability Custom VLSI Layout Using the Ulysses script environment, which considerably of the Weaver system (a knowledge-based Design Environment (Academic Press, reduces the power and authority circuit interconnections Boston, Massachusetts, 1988, 463 of the demonstration. This disappointing router) to restart, continue (that is, to pages) by Michael L. Bushnell deals demonstration might be the be interrupted), or accept that a user with an interesting and challenging result of the project's ambitious nature might specify some routing channels. A The book is misleading in its treatment achieve. The problem here is not the system called Ulysses that implements of some key points. Any routing expert blackboard architecture is described.

Databases are at the heart of most real-world knowledge base systems. The management and effective use of these databases will be the limiting factors in our ability to build ever more complex AI systems. This article reports on a workshop that explored how databases and their associated technologies can best be used in the development of large AI applications.

The vendors Based Systems, 355 pp., and Volume 2, techniques. They are interesting of knowledge-based-systems development Knowledge Acquisition Tools for Expert and informative, particularly tools, for example, Inference, Systems, 343 pp., Academic Press, San "Generalization and Noise" by Y. IntelliCorp, Aion, AI Corp., and IBM, Diego, California, 1988), edited by B. Kodratoff and M. Manango, which would do well to pay heed to these R. Gaines and J. H. Boose, is an excellent discusses symbolic and numeric rule books because they point the way to collection of papers useful to both induction.

Letters to the Editor.

Text planning is one of the most rapidly growing subfields of language generation. Until the 1988 AAAI conference, no workshop has concentrated on text planning and its relationship to realiza-tion. This report is a summary of that workshop.

These debates end by a culture for accommodating of the medical AI community, I feel I up merely as arguments in which its limited knowledge representations. Those of us in intelligence is). Depending such an extent that the limits of the medical AI have been highly sensitized upon what properties of human and computer system would no longer be to common misunderstandings artificial intelligence are stressed we a representational problem? We also encounter a general lack of of the relationship. Will we need to ascribe pleasure and realistic expectations regarding the The problem is that the models of pain to our computer experts?