Architecting a self-driving vehicle with a restricted dataset.
Case context: You are leading a project to build an autonomous vehicle, but your dataset of driving footage and corresponding controls is very small. You are deciding between two machine learning approaches: a purely end-to-end model that maps inputs directly to driving controls, or a pipeline model that first detects cars, then detects pedestrians, and finally plans a path.
Question: Based on the concept of function complexity and data requirements, which design path should you choose to ensure the system can be trained effectively with your limited data? Explain your decision.
Sample answer: You should choose the pipeline approach. An autonomous driving pipeline encodes three simpler subtasks: detecting other cars, detecting pedestrians, and planning a path. Because each of these steps is a relatively simpler function compared to mapping raw input to final path/controls directly, they can be learned with less training data than a purely end-to-end approach, making it the viable option for a restricted dataset.
Key points:
- Choose the pipeline approach over the end-to-end approach.
- The pipeline encodes three specific steps: detect cars, detect pedestrians, and plan a path.
- Each step in the pipeline represents a simpler function.
- Simpler functions require less data to learn, making it suitable for limited datasets.
Rubric: The answer must choose the pipeline approach and justify it by explaining that the three steps (detecting cars, detecting pedestrians, and planning a path) are simpler functions, which allows them to be learned with less data than a purely end-to-end approach.
0
1
Tags
Machine Learning
Deep Learning
Supervised Learning
Dive into Deep Learning @ D2L
Data Science
Machine Learning Strategy
Related
Which three key steps does the autonomous-driving pipeline encode, according to Machine Learning Yearning?
True or False: Each step in the autonomous-driving pipeline is a relatively simpler function that can be learned with less data than a purely end-to-end approach.
The autonomous-driving pipeline tells the algorithm that there are _____ key steps to driving.
Which three steps does the autonomous driving pipeline encode as key driving tasks, according to Machine Learning Yearning?
Each subtask in the autonomous driving pipeline requires more training data than a purely end-to-end approach would require.
The autonomous driving pipeline tells the algorithm that there are _____ key steps to driving.
Match each autonomous driving pipeline step to its primary function.
Place the three key driving steps in the order listed in Andrew Ng's autonomous driving pipeline in Machine Learning Yearning.
Why can each step in the autonomous driving pipeline be learned with less data than a purely end-to-end approach?
Using an autonomous driving pipeline explicitly tells the learning algorithm which key subtasks are involved in driving.
The third key step in the autonomous driving pipeline, after detecting cars and pedestrians, is to _____ for your car.
Match each concept to its description in the context of the autonomous driving pipeline from Machine Learning Yearning.
Order the reasoning steps a developer follows when deciding to use a pipeline approach for autonomous driving, from first to last.
Analyze the connection between function simplicity and data requirements in an autonomous driving pipeline.
Architecting a self-driving vehicle with a restricted dataset.
Describe the function complexity of each step in the autonomous driving pipeline relative to an end-to-end approach.