Summary of Reactxgb: a Hybrid Binary Convolutional Neural Network Architecture For Improved Performance and Computational Efficiency, by Po-hsun Chu and Ching-han Chen
ReActXGB: A Hybrid Binary Convolutional Neural Network Architecture for Improved Performance and Computational Efficiency
by Po-Hsun Chu, Ching-Han Chen
First submitted to arxiv on: 11 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computer Vision and Pattern Recognition (cs.CV)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a hybrid model called ReActXGB that addresses the challenges of reducing memory requirements and computational costs associated with deep neural networks (DNNs). By replacing the fully convolutional layer of ReActNet-A with XGBoost, the model achieves better performance while maintaining lower computational costs. The authors demonstrate the effectiveness of their approach on the FashionMNIST benchmark, showing a 1.47% improvement in top-1 accuracy and a reduction of 7.14% in floating-point operations (FLOPs) and 1.02% in model size. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary ReActXGB is a new way to build neural networks that uses less memory and computation than usual. The authors combined two different approaches, ReActNet-A and XGBoost, to create a better-performing model with lower costs. They tested this model on the FashionMNIST dataset and found it was more accurate by 1.47% and used fewer calculations and storage. |
Keywords
» Artificial intelligence » Xgboost
