P. Steiner

Learn More
The h'2 project aims to develop a distributed memory parallel processor (DMPP) that exploits the bene-jits of this class of machines, but appears to the user — and can be programmed and debugged — much like a conventional uniprocessor. To this end, we have concentrated our eflorts on the development of an automatically parallelizing compiler and a multiuser(More)
Motivation to study Hebbian learning arises from its neu-rophysiological plausibility and its suitability for hardware implementation. Up to now, artiicial Hebbian learning, embedded in a real system that performs adaptive motor control, has been restricted to one-layer networks. To overcome this limitation, a novel approach to adaptive pre-processing based(More)
  • 1