Traditional programmable computers are facing fundamental limitations in terms of speed and size, inspiring increasing interest in alternative paradigms such as neuromorphic computing. Researchers at IBM Research – Zurich and EPFL in Lausanne have now developed a spiking neural network computing architecture using phase-change memristors to mimic both the synapses and neurons in the neural system for the first time. They also demonstrate enhanced pattern and correlation distinguishing capabilities using a level-tuning mechanism similar to that found in the human auditory cortex.

Read the full article here.