The technology challenges and progress for Artificial Intelligence

DIPC Seminars

Christophe Rossel, IBM Research-Zurich Laboratory, Switzerland
Donostia International Physics Center
Add to calendar
Subscribe to Newsletter
The technology challenges and progress for Artificial Intelligence The world is excellent at creating huge amount of data. This is one of the reasons why we need technologies like Artificial Intelligence (AI), Machine Learning based on deep neural networks to make sense of these data. In a deep neural network the machine is built from millions of elementary units, or artificial ‘neurons’ that somewhat mimic the activity of the neurons in the brain. Today analog computing such as neuromorphic computing using non- volatile memories is looking beyond digital computing to get around the so- called von Neumann bottleneck. IBM Research is advancing hardware beyond traditional CMOS to see how far we can push performance. This hardware exploits the storage capability and physical attributes of phase-change memory (PCM) devices arranged in crossbar configuration. Some simple demonstrations with analog AI chip are available online. Host: Ricardo Diez Muino