Bringing AI to edge: From deep learning's perspective

D Liu, H Kong, X Luo, W Liu, R Subramaniam - Neurocomputing, 2022 - Elsevier
Edge computing and artificial intelligence (AI), especially deep learning algorithms, are
gradually intersecting to build the novel system, namely edge intelligence. However, the …

Latency-constrained DNN architecture learning for edge systems using zerorized batch normalization

S Huai, D Liu, H Kong, W Liu, R Subramaniam… - Future Generation …, 2023 - Elsevier
Deep learning applications have been widely adopted on edge devices, to mitigate the
privacy and latency issues of accessing cloud servers. Deciding the number of neurons …

Efficient Deep Learning Infrastructures for Embedded Computing Systems: A Comprehensive Survey and Future Envision

X Luo, D Liu, H Kong, S Huai, H Chen… - ACM Transactions on …, 2024 - dl.acm.org
Deep neural networks (DNNs) have recently achieved impressive success across a wide
range of real-world vision and language processing tasks, spanning from image …

Parameter Space Exploration of Neural Network Inference Using Ferroelectric Tunnel Junctions for Processing-In-Memory

S Hosseinzadeh, S Lancaster… - 2024 27th Euromicro …, 2024 - ieeexplore.ieee.org
This paper explores CMOS-compatible Ferroelectric Tunnel Junctions (FTJs) for Processing-
In-Memory (PIM) to address the 'memory wall'in traditional computing. A novel FTJ noise …

Enabling efficient edge intelligence: a hardware-software codesign approach

S Huai - 2023 - dr.ntu.edu.sg
Deep Neural Networks (DNNs) have made significant advancements in various domains,
including computer vision (CV), natural language processing (NLP), etc. With the Internet of …

Adaptive neural networks for edge intelligence

H Kong - 2023 - dr.ntu.edu.sg
Deep neural networks (DNNs) have achieved remarkable results and have become the
mainstay of many applications including autonomous driving and emerging AI-enabled …