Lekai Song
YOU?
Author Swipe
View article: Carbon nanotube analog tensor core accelerating edge computer vision
Carbon nanotube analog tensor core accelerating edge computer vision Open
Computer vision requires intense tensor operations, primarily matrix multiplications, imposing substantial computation demands. Using hardware such as GPU and ASICs for acceleration offers a viable solution. However, their application at e…
View article: Chip-scale reconfigurable carbon nanotube physical unclonable functions
Chip-scale reconfigurable carbon nanotube physical unclonable functions Open
With the rapid advancement of edge intelligence, ensuring the security of edge devices and protecting their communication has become critical. Physical unclonable functions, known as hardware fingerprints , are an emerging hardware securit…
View article: Hardware Implementation of Bayesian Decision‐Making with Memristors
Hardware Implementation of Bayesian Decision‐Making with Memristors Open
Brains perform decision‐making by Bayes theorem – events are quantified as probabilities and based on probability rules, computed to render the decisions. Learning from this, Bayes theorem may be applied to enable efficient user–scene inte…
View article: Lightweight error-tolerant edge detection using memristor-enabled stochastic computing
Lightweight error-tolerant edge detection using memristor-enabled stochastic computing Open
The demand for efficient edge computer vision has spurred the development of stochastic computing for image processing. Memristors, by introducing their inherent switching stochasticity into computation, readily enable stochastic image pro…
View article: Hardware implementation of timely reliable Bayesian decision-making using memristors
Hardware implementation of timely reliable Bayesian decision-making using memristors Open
Brains perform decision-making by Bayes theorem. The theorem quantifies events as probabilities and, based on probability rules, renders the decisions. Learning from this, Bayes theorem can be applied to enable efficient user-scene interac…
View article: Self-reconfigurable multifunctional memristive nociceptor for intelligent robotics
Self-reconfigurable multifunctional memristive nociceptor for intelligent robotics Open
Artificial nociceptors, mimicking human-like stimuli perception, are of significance for intelligent robotics to work in hazardous and dynamic scenarios. One of the most essential characteristics of the human nociceptor is its self-adjusta…
View article: Harnessing Physical Entropy Noise in Structurally Metastable 1T′ Molybdenum Ditelluride for True Random Number Generation
Harnessing Physical Entropy Noise in Structurally Metastable 1T′ Molybdenum Ditelluride for True Random Number Generation Open
True random numbers are crucial for various research and engineering problems. Their generation depends upon a robust physical entropy noise. Here, we present true random number generation from the conductance noise probed in structurally …
View article: Scalable Synaptic Transistor Memory from Solution‐Processed Carbon Nanotubes for High‐Speed Neuromorphic Data Processing
Scalable Synaptic Transistor Memory from Solution‐Processed Carbon Nanotubes for High‐Speed Neuromorphic Data Processing Open
Neural networks as a core information processing technology in machine learning and artificial intelligence demand substantial computational resources to deal with the extensive multiply‐accumulate operations. Neuromorphic computing is an …
View article: Self-reconfigurable Multifunctional Memristive Nociceptor for Intelligent Robotics
Self-reconfigurable Multifunctional Memristive Nociceptor for Intelligent Robotics Open
Artificial nociceptors, mimicking human-like stimuli perception, are of significance for intelligent robotics to work in hazardous and dynamic scenarios. One of the most essential characteristics of the human nociceptor is its self-adjusta…
View article: Analysis on reservoir activation with the nonlinearity harnessed from solution-processed molybdenum disulfide
Analysis on reservoir activation with the nonlinearity harnessed from solution-processed molybdenum disulfide Open
Reservoir computing is a recurrent neural network designed for approximating complex dynamics in, for instance, motion tracking, spatial-temporal pattern recognition, and chaotic attractor reconstruction. Its implementation demands intense…
View article: Lightweight, error-tolerant edge detection using memristor-enabled stochastic logics
Lightweight, error-tolerant edge detection using memristor-enabled stochastic logics Open
The demand for efficient edge vision has spurred the interest in developing stochastic computing approaches for performing image processing tasks. Memristors with inherent stochasticity readily introduce probability into the computations a…
View article: Conduction Modulation of Solution‐Processed 2D Materials
Conduction Modulation of Solution‐Processed 2D Materials Open
Solution‐processed 2D materials hold promise for their scalable applications. However, the random, fragmented nature of the solution‐processed nanoflakes and the poor percolative conduction through their discrete networks limit the perform…
View article: Spiking Neurons with Neural Dynamics Implemented Using Stochastic Memristors
Spiking Neurons with Neural Dynamics Implemented Using Stochastic Memristors Open
Implementing and integrating spiking neurons for neuromorphic hardware realization conforming to spiking neural networks holds great promise in enabling efficient learning and decision‐making. The spiking neurons, however, may lack the spi…
View article: Conduction modulation of solution-processed two-dimensional materials
Conduction modulation of solution-processed two-dimensional materials Open
Solution-processed two-dimensional (2D) materials hold promise for their scalable applications. However, the random, fragmented nature of the solution-processed nanoflakes and the poor percolative conduction through their discrete networks…
View article: Essential Characteristics of Memristors for Neuromorphic Computing (Adv. Electron. Mater. 2/2023)
Essential Characteristics of Memristors for Neuromorphic Computing (Adv. Electron. Mater. 2/2023) Open
Memristors Memristive neuromorphic computing promotes the development of humanoid robotics, and its performance is directly affected by the memristors' characteristics. In article number 2200833, Wenbin Chen, Shuo Gao, and co-workers overv…
View article: Memristor‐Based Intelligent Human‐Like Neural Computing
Memristor‐Based Intelligent Human‐Like Neural Computing Open
Humanoid robots, intelligent machines resembling the human body in shape and functions, cannot only replace humans to complete services and dangerous tasks but also deepen the own understanding of the human body in the mimicking process. N…
View article: Essential Characteristics of Memristors for Neuromorphic Computing
Essential Characteristics of Memristors for Neuromorphic Computing Open
The memristor is a resistive switch where its resistive state is programable based on the applied voltage or current. Memristive devices are thus capable of storing and computing information simultaneously, breaking the Von Neumann bottlen…