IN THIS ISSUE: Machines That Learn and Recall: Their Beginnings in Research on Neural-Like Processing of Signals /2 (Wolfgang Sachse, Cornell professor of theoretical and applied mechanics, discusses how a neural-like processor can be used to analyze ultrasonic signals in materials testing.) ... Explanation-Based Learning for Machines /8 (A recent development in the field of artificial intelligence is research on machine learning that is deductive in nature and well suited to problem-solving tasks. Alberto Maria Segre, an assistant professor in Cornell's Department of Computer Science, discusses his work in this area.) ... Raising the IQ of a Robot : Reformulation of Symbolic Representations /15 (One representational law that a smart robot has to obey is: Make the fewest distinctions necessary to achieve the goal. A method of automatically obtaining this result is explained by Devika Subramanian, an assistant professor of computer science at Cornell.) ... Register /22 ... Faculty Publications /28