On the Sample Complexity of End-to-end Training vs. Semantic Abstraction Training
arXiv:1604.06915
Abstract
We compare the end-to-end training approach to a modular approach in which a system is decomposed into semantically meaningful components. We focus on the sample complexity aspect, in the regime where an extremely high accuracy is necessary, as is the case in autonomous driving applications. We demonstrate cases in which the number of training examples required by the end-to-end approach is exponentially larger than the number of examples required by the semantic abstraction approach.
References in corpus (1)
Cited by in corpus (14)
- Multimodal End-to-End Autonomous Driving
- An Analysis of ISO 26262: Using Machine Learning Safely in Automotive Software
- F1/10: An Open-Source Autonomous Cyber-Physical Platform
- Failures of Gradient-Based Deep Learning
- Predicting Deeper into the Future of Semantic Segmentation
- MADRaS : Multi Agent Driving Simulator
- DSAC - Differentiable RANSAC for Camera Localization
- Closing the gap towards end-to-end autonomous vehicle system
- Future Segmentation Using 3D Structure
- Feature Analysis and Selection for Training an End-to-End Autonomous Vehicle Controller Using the Deep Learning Approach
- On the Ethics of Building AI in a Responsible Manner
- An Optimized Signal Processing Pipeline for Syllable Detection and Speech Rate Estimation
- Discovery and usage of joint attention in images
- Recurrent Flow-Guided Semantic Forecasting