End to End
"End-to-end" systems aim to streamline complex processes by integrating multiple stages into a single, unified model, eliminating the need for intermediate steps and potentially improving efficiency and performance. Current research focuses on applying this approach across diverse fields, utilizing architectures like transformers, reinforcement learning, and spiking neural networks to tackle challenges in autonomous driving, robotics, speech processing, and natural language processing. This approach offers significant potential for improving the accuracy, speed, and robustness of various applications, while also simplifying development and deployment.
Papers
An end-to-end framework for gene expression classification by integrating a background knowledge graph: application to cancer prognosis prediction
Kazuma Inoue, Ryosuke Kojima, Mayumi Kamada, Yasushi Okuno
End-to-End Learnable Multi-Scale Feature Compression for VCM
Yeongwoong Kim, Hyewon Jeong, Janghyun Yu, Younhee Kim, Jooyoung Lee, Se Yoon Jeong, Hui Yong Kim
PINQI: An End-to-End Physics-Informed Approach to Learned Quantitative MRI Reconstruction
Felix F Zimmermann, Christoph Kolbitsch, Patrick Schuenke, Andreas Kofler
Learning an Interpretable End-to-End Network for Real-Time Acoustic Beamforming
Hao Liang, Guanxing Zhou, Xiaotong Tu, Andreas Jakobsson, Xinghao Ding, Yue Huang
An End-to-End Reinforcement Learning Approach for Job-Shop Scheduling Problems Based on Constraint Programming
Pierre Tassel, Martin Gebser, Konstantin Schekotihin
Improving Frame-level Classifier for Word Timings with Non-peaky CTC in End-to-End Automatic Speech Recognition
Xianzhao Chen, Yist Y. Lin, Kang Wang, Yi He, Zejun Ma