About this Abstract |
Meeting |
MS&T22: Materials Science & Technology
|
Symposium
|
Advances in Emerging Electronic Nanomaterials: Synthesis, Enhanced Properties, Integration, and Applications
|
Presentation Title |
Two Dimensional Materials for Neuromorphic Computing |
Author(s) |
Tania Roy |
On-Site Speaker (Planned) |
Tania Roy |
Abstract Scope |
Advances in machine learning and artificial intelligence has been mainly from the architecture and software levels, with the basic building blocks still being CMOS transistors. This causes the hardware to be bulky and power-hungry. Our group is developing neuromorphic devices functioning similar to the neurons and synapses of the human brain, which can serve as the basic building blocks of neural network hardware, making the systems energy-efficient, scalable and compact. In this talk, I will discuss the use of novel semiconducting two-dimensional materials to make artificial neurons and synapses which can perform pattern recognition. The layered structure of 2D materials allows great control over the synaptic characteristics. I will also discuss our efforts in developing optoelectronic synapses which, similar to optic nerves, combine the functions of photodetectors with analog memory. These devices can provide an avenue towards inference tasks at the edge in an era of data deluge. |