3D-Integrated Neuromorphic Hardware With A Two-Level Neuromorphic “Synapse Over Neuron” Structure


A technical paper titled “3D Neuromorphic Hardware with Single Thin-Film Transistor Synapses Over Single Thin-Body Transistor Neurons by Monolithic Vertical Integration” was published by researchers at Korea Advanced Institute of Science and Technology (KAIST) and SK hynix.


“Neuromorphic hardware with a spiking neural network (SNN) can significantly enhance the energy efficiency for artificial intelligence (AI) functions owing to its event-driven and spatiotemporally sparse operations. However, an artificial neuron and synapse based on complex complementary metal-oxide-semiconductor (CMOS) circuits limit the scalability and energy efficiency of neuromorphic hardware. In this work, a neuromorphic module is demonstrated composed of synapses over neurons realized by monolithic vertical integration. The synapse at top is a single thin-film transistor (1TFT-synapse) made of poly-crystalline silicon film and the neuron at bottom is another single transistor (1T-neuron) made of single-crystalline silicon. Excimer laser annealing (ELA) is applied to activate dopants for the 1TFT-synapse at the top and rapid thermal annealing (RTA) is applied to do so for the 1T-neuron at the bottom. Internal electro-thermal annealing (ETA) via the generation of Joule heat is also used to enhance the endurance of the 1TFT-synapse without transferring heat to the 1T-neuron at the bottom. As neuromorphic vision sensing, classification of American Sign Language (ASL) is conducted with the fabricated neuromorphic module. Its classification accuracy on ASL is ≈92.3% even after 204 800 update pulses.”

Find the technical paper here. Published September 2023.

Han, Joon‐Kyu, Jung‐Woo Lee, Yeeun Kim, Young Bin Kim, Seong‐Yun Yun, Sang‐Won Lee, Ji‐Man Yu, Keon Jae Lee, Hyun Myung, and Yang‐Kyu Choi. “3D Neuromorphic Hardware with Single Thin‐Film Transistor Synapses Over Single Thin‐Body Transistor Neurons by Monolithic Vertical Integration.” Advanced Science (2023): 2302380.

Related Reading
Will Floating Point 8 Solve AI/ML Overhead?
Less precision equals lower power, but standards are required to make this work.


Leave a Reply

(Note: This name will be displayed publicly)