(115e) Neuromorphic Computing with the Redox Transistor

Inspired by the efficiency of the brain, CMOS-based neural architectures and memristors are being developed for pattern recognition and machine learning. However, the volatility, design complexity and high supply voltages for CMOS architectures, and the stochastic and energy-costly switching of memristors complicate the path to achieve the interconnectivity, information density, and energy efficiency of the brain using either approach. In my talk, I will review the latest advances in neuromorphic computing architectures based on deep neural networks implemented using CMOS and memristors and describe the challenges in achieving both high accuracy and energy efficiency using these devices. I will then discuss an alternative approach based on the redox transistor: a device with a resistance switching mechanism fundamentally different from existing memristors, involving the reversible, electrochemical reduction/oxidation of a material to tune its electronic conductivity. I will first describe an inorganic redox transistor based upon the intercalation of Li-ion dopants into a channel of a Li intercalation material such as Li_xCoO₂, a common Li intercalation material, or Li_xMoO₃, a 2D layered oxide. These Li-ion synaptic transistors for analog computing (LISTA) switch at low voltage (mVs) and energy, display hundreds of distinct, non-volatile conductance states, and achieve high classification accuracy when implemented in neural network simulations. I will also discuss a redox transistor based on the polymer system PEDOT:PSS, and which we also call the electrochemical neuromorphic organic device (ENODe). Plastic ENODes are fabricated on flexible substrates enabling the integration of neuromorphic functionality in stretchable electronic systems. Mechanical flexibility makes ENODes compatible with three-dimensional architectures, opening a path towards extreme interconnectivity comparable to the human brain. Finally, I will demonstrate how these elements can be integrated into functional neuromorphic computing arrays.