Frontiers of Deep Learning: From Novel Application to Real-World Deployment

TL;DR

This paper reviews recent advances in deep learning applications, focusing on transformer-based image enhancement and in-storage computing for recommendation systems, highlighting progress from novel methods to real-world deployment.

Contribution

It provides a comparative analysis of two recent deep learning research papers, emphasizing their innovative techniques and potential future research directions.

Findings

Transformer networks improve SAR image quality by reducing speckle noise.

In-storage computing enables cost-efficient, high-performance deep learning recommendation systems.

Deep learning's impact spans diverse fields, from image processing to recommendation systems.

Abstract

Deep learning continues to re-shape numerous fields, from natural language processing and imaging to data analytics and recommendation systems. This report studies two research papers that represent recent progress on deep learning from two largely different aspects: The first paper applied the transformer networks, which are typically used in language models, to improve the quality of synthetic aperture radar image by effectively reducing the speckle noise. The second paper presents an in-storage computing design solution to enable cost-efficient and high-performance implementations of deep learning recommendation systems. In addition to summarizing each paper in terms of motivation, key ideas and techniques, and evaluation results, this report also presents thoughts and discussions about possible future research directions. By carrying out in-depth study on these two representative papers and related references, this doctoral candidate has developed better understanding on the far-reaching impact and efficient implementation of deep learning models.