Emerging Processor Technologies & Neuromorphic Engineering: The Quest for Brain-like Computers
The history of computing and computing hardware has been a very interesting journey with the needs for being performance hungry and power hungry being the two key shifts in the industry. The first part of the talk will give you a glimpse of some of these interesting facts of the past, present and future. Neurobiological processing systems are remarkable computational devices. Their basic computing elements, the neurons, are slow, heterogeneous and stochastic in nature, and yet they outperform today’s most powerful computers at real-world tasks such as vision, audition, and motor control. The loss of merely one transistor can wreck a microprocessor, but brains lose neurons all the time without losing functionality. This talk is about a generic and low-power trainable IC that is inspired by the principles of biological neural population coding and about a NeuroElectronic hybrid-system wherein a biological-neural-network will be interfaced with silicon-neurons built on a neuromorphic-chip.