A bistable mechanism has two stable states within its range of motion. Its advantages include the ability to stay in two positions without power input and despite small external disturbances. Therefore, bistable micro-mechanisms could allow the creation of MEMS with improved energy efficiency and positioning accuracy. This paper presents bistable micro-mechanisms which function within the plane of fabrication. These bistable mechanisms, called “Young” bistable mechanisms, obtain their energy storage characteristics from the deflection of two compliant members. They have two pin joints connected to the substrate, and can be constructed of two layers of polysilicon. The pseudo-rigid-body model is used to analyze and design these mechanisms. This approach allows greater freedom and flexibility in the design process. The mechanisms were fabricated and tested to demonstrate their bistable behavior and to determine the repeatability of their stable positions.

A bst r actThis paper presents a VLSI implementation of the Priority Adaptive Self-organizing Concurrent System (PASOCS) learning model that is built using a multichip module (MCM) substrate. Many current hardware implementations of neural network learning models are direct implementations of classical neural network structures-a large number of sample computing nodes connected by a dense number of weighted links. PASOCS is one of a class of ASOCS (Adaptive SelfOrganizing Concurrent System) connectionist models whose overall goal is the same as classical neural networks models, but whose functional mechanisms differ significantly. This model has potential application in areas such as pattern recognition, ro botics, logical inference, and dynamic control.

No abstract

The requirement for dense interconnect in artificial neural network systems has led researchers to seek high-density interconnect technologies. This paper reports an implementation using multi-chip modules (MCMs) as the interconnect medium. The specific system described is a self-organizing, parallel, and dynamic learning model which requires a dense interconnect technology for effective implementation; this requirement is fulfilled by exploiting MCM technology. The ideas presented in this paper regarding an MCM implementation of artificial neural networks are versatile and can be adapted to apply to other neural network and connectionist models.

No abstract