Artificial Synaptic Memory for Computers And Other Intelligent Systems

Electrochemical RAM Mimicking Human Synapses

Researchers at the KTH Royal Institute of Technology developed an electrochemical RAM that mimics human synapses. This high-speed ionic Synaptic Memory is made from 2D Titanium Carbide MXene. Various aspects of this material can be evaluated using relevant techniques in metrology testing labs. Electrochemical Random-Access Memory (ECRAM) is a type of non-volatile memory (NVM). Non-volatile memory (NVM) can be leveraged for in-memory compute, thereby reducing the frequency of data transfer between storage and processing units. This can ultimately improve compute time and energy efficiency over hierarchical system architectures by eliminating the Von Neumann bottleneck.

Traditional resistive memories suffer from high write noise and asymmetric conductance tuning, preventing parallel programming of ANN arrays. Electrochemical random-access memories (ECRAMs), where resistive switching occurs by ion insertion into a redox-active channel, aim to address these challenges due to their linear switching and low noise. Metrology testing labs are equipped to test various raw materials as required. 

“Instead of transistors that are either on or off, and the need for information to be carried back and forth between the processor and memory—these new computers rely on components that can have multiple states, and perform in-memory computation,” Hamedi says. Metrology testing techniques are very useful for all the evaluations needed.

ECRAMs using 2D materials and metal oxides however suffer from slow ion kinetics, whereas organic ECRAMs enable high-speed operation but face challenges toward very large scale chip integration due to poor temperature stability of polymers. Temperature stability of polymers can be determined in accelerated aging testing labs. Here, ECRAMs uses 2D titanium carbide (Ti3C2Tx). Researchers demonstrated MXene that combines the high speed of organics and the integration compatibility of inorganic materials in a single high-performance device. These ECRAMs combine the speed, linearity, write noise, switching energy, and endurance metrics essential for parallel acceleration of ANNs, and importantly, they are stable after heat treatment needed for back-end-of-line integration with Si electronics.

“MXenes are an exciting materials family for this particular application as they combine the temperature stability needed for integration with conventional electronics with the availability of a vast composition space to optimize performance” says Salleo. Metrology testing labs are equipped to test various raw materials as required. More theoretical work, empirical work, and material testing is needed. Although there is a long way to go before consumers can buy their own neuromorphic computers, the 2D electrochemical RAM is a significant breakthrough towards artificial intelligence that can solve confusing problems with very minimal energy consumption.

Reference:

“High-Speed Ionic Synaptic Memory Based on 2D Titanium Carbide MXene” by Armantas Melianas, Min-A Kang, Armin VahidMohammadi, Tyler James Quill, Weiqian Tian, Yury Gogotsi, Alberto Salleo and Mahiar Max Hamedi, 21 November 2021, Advanced Functional Materials. DOI: 10.1002/adfm.202109970

Source: https://scitechdaily.com/high-speed-ionic-synaptic-memory-simulating-brain-synapses-in-computers-with-2d-materials/