The continuous-time mathematics of a binary-decision making neuromime are presented. The model, generally describable as a simplification of the Hodgkin-Huxley model, seeks to mimic many properties of biological neurons including spatial and temporal summation of excitatory and inhibitory inputs, action potential evolution controlled by countervailing charge movements, and postinhibitory rebound...
The task of inductive learning from examples places constraints on the representation of training instances and concepts. These constraints are different from, and often incompatible with, the constraints placed on the representation by the performance task. This incompatibility explains why previous researchers have found it so difficult to construct good...
Beacons are defined as sets of key features that typically indicate the presence of a particular data structure or operation. It has been claimed that programmers use them to help comprehend an unfamiliar program. However, despite their importance, beacons are not well-defined and very few have been identified. The present...
Asmodeus is a distributed database system which simplifies the tasks of the Unix systems administrator. Using simple commands to the Asmodeus command interface, the systems administrator can perform many tedious operations over a large network of machines. The system uses a reliable datagram socket connection for all of its communication....
In this paper we study the problem of scheduling parallel program tasks that are enclosed in a set of nested loops on parallel computers. We first introduce a representation of the tasks and their relations in a loop. The representation allows us to express loop-carried data dependences among tasks as...
We provide a new solution to the problem of scheduling parallel program tasks that are enclosed in a set of nested loops on distributed-memory parallel computers. The new solution is extended to a new scheduling heuristic for scheduling unrolled loops onto arbitrary target machines. Our technique allows several iterations of...
The performance of the error backpropagation (BP) and ID3 learning algorithms was compared on the task of mapping English text to phonemes and stresses. Under the distributed output code developed by Sejnowski and Rosenberg, it is shown that BP consistently out-performs 1D3 on this task by several percentage points. Three...
Exploratory research contributes to the continued vitality of every discipline. The aim of exploratory research is to identify new tasks-tasks that cannot be solved by existing methods. Once a new task has been found, exploratory research seeks to develop a precise definition of the task and to understand the factors...
The performance of the error backpropagation (BP) and 1D3 learning algorithms was com- pared on the task of mapping English text to phonemes and stresses. Under the distributed output code developed by Sejnowski and Rosenberg, it is shown that BP consistently out- performs ID3 on this task by several percentage...
It is suggested that the best way to learn about a Macintosh application is to play around with it. We agree with this philosophy and believe that most of the features in the Parallel Programming Support Environment (or PPSE) are easy enough to learn without referring to this manual. Most...