Learn Before
Deciding the Architecture for a New Self-Driving Startup
Case context: A new autonomous vehicle startup is deciding how to build its perception and control stack. One team proposes a single deep neural network that takes in camera feeds and directly outputs steering angles. Another team proposes a modular pipeline that first detects cars and pedestrians, and then plans the path. They currently have limited full end-to-end driving logs but a lot of isolated bounding box data.
Question: Based on Machine Learning Yearning, which approach should the startup choose and why?
Sample answer: The startup should choose the modular, non-end-to-end approach. According to Machine Learning Yearning, an end-to-end approach is less promising for autonomous driving until more end-to-end data becomes available. Because they have limited end-to-end driving logs but abundant isolated data, a non-end-to-end architecture better matches their current data availability.
Key points:
- Recommend the modular/non-end-to-end approach.
- Identify that end-to-end data is currently limited.
- State that non-end-to-end architecture better matches the available data.
Rubric: The student must recommend the non-end-to-end (modular) approach and justify it by stating that its architecture better matches the availability of data.
0
1
Tags
Machine Learning
Deep Learning
Supervised Learning
Dive into Deep Learning @ D2L
Data Science
Machine Learning Strategy
Machine Learning Yearning @ DeepLearning.AI
Related
Why does Machine Learning Yearning consider the non-end-to-end approach more promising for autonomous driving?
True or False: According to Machine Learning Yearning, end-to-end learning is always the best ML approach regardless of the domain.
Until more _____ becomes available, the non-end-to-end approach is significantly more promising for autonomous driving.
Match each term to its correct description in the context of end-to-end learning for autonomous driving.
Order the reasoning steps Machine Learning Yearning uses to conclude the non-end-to-end approach is better for autonomous driving.
Which application does Machine Learning Yearning explicitly cite as a successful example of end-to-end learning?
True or False: The non-end-to-end approach is preferred for autonomous driving because its architecture better matches the availability of data.
An end-to-end autonomous driving model takes in _____ and directly outputs the steering direction.
Match each data availability scenario to the approach it favors for autonomous driving, per Machine Learning Yearning.
Order the steps for deciding between end-to-end and non-end-to-end approaches for a new ML task, per Machine Learning Yearning's reasoning.
Analyzing the Skepticism of End-to-End Autonomous Driving
Deciding the Architecture for a New Self-Driving Startup
Requirement for End-to-End Autonomous Driving