Convolutional Neural Networks: Co-Design of Hardware Architecture and Compression Algorithm


Researchers at Soongsil University (Korea) published “A Survey on Efficient Convolutional Neural Networks and Hardware Acceleration.”

“Over the past decade, deep-learning-based representations have demonstrated remarkable performance in academia and industry. The learning capability of convolutional neural networks (CNNs) originates from a combination of various feature extraction layers that fully utilize a large amount of data. However, they often require substantial computation and memory resources while replacing traditional hand-engineered features in existing systems. In this review, to improve the efficiency of deep learning research, we focus on three aspects: quantized/binarized models, optimized architectures, and resource-constrained systems. Recent advances in light-weight deep learning models and network architecture search (NAS) algorithms are reviewed, starting with simplified layers and efficient convolution and including new architectural design and optimization. In addition, several practical applications of efficient CNNs have been investigated using various types of hardware architectures and platforms.”

Find the technical paper here. Published March 2022.

Ghimire, D.; Kil, D.; Kim, S.-h. A Survey on Efficient Convolutional Neural Networks and Hardware Acceleration. Electronics 2022, 11, 945. https://doi.org/10.3390/electronics11060945.

Related Reading
How To Optimize A Processor
There are at least three architectural layers to processor design, each of which plays a significant role.
New Uses For AI In Chips
ML/DL is increasing design complexity at the edge, but it’s also adding new options for improving power and performance.
Why Hardware-Dependent Software Is So Critical
It may not be the most glamorous type of software development, but getting it right is essential for the success of any hardware platform.

Leave a Reply

(Note: This name will be displayed publicly)