A comprehensive review of model compression techniques in machine learning

PV Dantas, W Sabino da Silva Jr, LC Cordeiro… - Applied …, 2024 - Springer
This paper critically examines model compression techniques within the machine learning
(ML) domain, emphasizing their role in enhancing model efficiency for deployment in …

Neuromorphic computing using NAND flash memory architecture with pulse width modulation scheme

ST Lee, JH Lee - Frontiers in Neuroscience, 2020 - frontiersin.org
A novel operation scheme is proposed for high-density and highly robust neuromorphic
computing based on NAND flash memory architecture. Analog input is represented with time …

[HTML][HTML] Investigation of deep spiking neural networks utilizing gated Schottky diode as synaptic devices

ST Lee, JH Bae - Micromachines, 2022 - mdpi.com
Deep learning produces a remarkable performance in various applications such as image
classification and speech recognition. However, state-of-the-art deep neural networks …

Memristive crossbar circuit for neural network and its application in digit recognition

X Wan, N He, D Liang, W Xu, L Wang… - Japanese Journal of …, 2022 - iopscience.iop.org
A neural network fully implemented by memristive crossbar circuit is proposed and
simulated, which can operate in parallel for the entire process. During the forward …

[CITA][C] Structured pruning 을 활용한 hardware spiking neural network 경량화

전보성, 장태진, 박병국 - 대한전자공학회 학술대회, 2022 - dbpia.co.kr
In this paper, we evaluate a structured pruning to compress the hardware-based spiking
neural network (SNN). Since CMOS neuron circuit has a larger area than the synaptic …