Publications by authors named "Sangmin Yoo"
Article Synopsis
- - The study presents a lithium-doped silicate resistive random access memory (RRAM) device with a titanium nitride (TiN) electrode that simulates biological synapses by allowing fine-tuned control over analog synaptic properties.
- - The device utilizes the low ionization energy of lithium ions for dynamic operation, achieving both short-term and long-term memory emulation, along with features like synaptic plasticity and decay that mimic biological learning processes.
- - By replicating learning rules found in the human brain, such as spike-timing-dependent plasticity and synaptic pruning, this technology has the potential to enhance the development of efficient neuromorphic computing systems.
Digital computing is nearing its physical limits as computing needs and energy consumption rapidly increase. Analogue-memory-based neuromorphic computing can be orders of magnitude more energy efficient at data-intensive tasks like deep neural networks, but has been limited by the inaccurate and unpredictable switching of analogue resistive memory. Filamentary resistive random access memory (RRAM) suffers from stochastic switching due to the random kinetic motion of discrete defects in the nanometer-sized filament.
View Article and Find Full Text PDF