Chalcogenide Optomemristors for Multi-factor Neuromorphic Computation
Overview
Affiliations
Neuromorphic hardware that emulates biological computations is a key driver of progress in AI. For example, memristive technologies, including chalcogenide-based in-memory computing concepts, have been employed to dramatically accelerate and increase the efficiency of basic neural operations. However, powerful mechanisms such as reinforcement learning and dendritic computation require more advanced device operations involving multiple interacting signals. Here we show that nano-scaled films of chalcogenide semiconductors can perform such multi-factor in-memory computation where their tunable electronic and optical properties are jointly exploited. We demonstrate that ultrathin photoactive cavities of Ge-doped Selenide can emulate synapses with three-factor neo-Hebbian plasticity and dendrites with shunting inhibition. We apply these properties to solve a maze game through on-device reinforcement learning, as well as to provide a single-neuron solution to linearly inseparable XOR implementation.
Memristive Ion Dynamics to Enable Biorealistic Computing.
Zhao R, Kim S, Xu Y, Zhao J, Wang T, Midya R Chem Rev. 2024; 125(2):745-785.
PMID: 39729346 PMC: 11759055. DOI: 10.1021/acs.chemrev.4c00587.
Energy-Efficient Integrated Electro-Optic Memristors.
He Y, Farmakidis N, Aggarwal S, Dong B, Lee J, Wang M Nano Lett. 2024; 24(51):16325-16332.
PMID: 39658825 PMC: 11674150. DOI: 10.1021/acs.nanolett.4c04567.
Cellular mechanisms of cooperative context-sensitive predictive inference.
Marvan T, Phillips W Curr Res Neurobiol. 2024; 6:100129.
PMID: 38665363 PMC: 11043869. DOI: 10.1016/j.crneur.2024.100129.
Wang K, Liao Y, Li W, Li J, Su H, Chen R Nat Commun. 2024; 15(1):3505.
PMID: 38664383 PMC: 11045776. DOI: 10.1038/s41467-024-47641-6.