#MICROCHIP Memristor emulates neural learning #Semiconductor

In the 1960s Ted Hoff--who later invented the microprocessor at Intel--suggested to his Ph.D. adviser--Bernard Widrow--that a new type of circuit element was needed to make brain-like devices--they later called it a memistor. Now Hewlett Packard is picking up the ball 50 years later with its memristor, which uses different materials but is still aimed at emulating the brain. Look for a flurry of memristor announcements throughout the rest of 2010. R.C.J.


Synapses are the bit-cells of the brain, and they behave more like memristors than any other electronic circuit element, according to the University of Michigan researchers who recently demonstrated that a single memristor can learn using the same technique as the human brain. Researchers demonstrate memristors emulating the learning function of a neural network by changing the strength of its synaptic connections in response to synchronized voltage spikes. Neural networks can learn patterns that are too difficult for engineers to craft as specific algorithms, but they depend on an analog memory element called a synapse, which today is simulated on supercomputers as a numerical value. Learning occurs when simultaneous voltage spikes are generated from feature detectors in the senses, like edge detectors in the eye. When the simultaneous spikes come in, say from the edge detectors in both eyes, the receiving synapse in the brain responds by increasing its value--a digit used for supercomputer simulations. Instead, memristors change their resistance value.
Full Text: http://bit.ly/9UVjwM