CogniGron Seminar: Scott Keene (Stanford University, USA) - "Organic resistive memory devices for neuromorphic computing"
When: | Th 28-06-2018 13:00 - 14:00 |
Where: | 5159.0062 (Energy Academy Europe) |
Neuromorphic computing could address the inherent inefficiencies of the von Neumann architecture for dedicated machine learning applications by utilizing parallel operation. Recent work on silicon-based asynchronous spiking neural networks and large crossbar-arrays of two-terminal memristive devices has led to the development of promising neuromorphic systems. However, delivering a parallel computation technology capable of implementing compact and efficient artificial neural networks in hardware remains a significant challenge. Organic electronic materials offer an attractive alternative to such systems and could provide neuromorphic devices with low-energy switching and excellent tunability, while being biocompatible and relatively inexpensive.
This talk describes state-of-the-art organic neuromorphic devices and provides an overview of the current challenges in the field and attempts to address them1. We demonstrate a novel concept based on an organic electrochemical transistor2 and show how some challenges in the field such as stability, linearity and state retention can be overcome3. Furthermore, we show that through downscaling of organic neuromorphic devices and engineering the channel layer, we can achieve the fast speed (~1 μs) and low currents (~10 nA) required for an array of neuromorphic devices. Finally, we show recent progress towards integration of organic neuromorphic devices with non-linear filament forming switches to achieve parallel programming of a neuromorphic array.
1. van de Burgt et al. Nature Electronics, 2018
2. van de Burgt et al. Nature Materials, 2017
3. Keene et al. J Phys D, 2018
Contact & more about Scott:
Scott Keene received his B.S. in Materials Science and Engineering from the University of Washington in 2015 where he graduated with departmental honors. He worked with Prof. Marco Rolandi as an undergraduate researcher at the University of Washington from 2014 to 2015. He is now pursuing his Ph.D. in Materials Science and Engineering at Stanford University under the mentorship of Prof. Alberto Salleo. He received the Stanford Graduate Fellowship from the Stanford Office of Technology Licensing in 2015. His research interests include electrochemical interactions in semiconducting polymers for organic devices including neuromorphic memory and wearable biosensors.
e-mail: stkeene@stanford.edu