Evaluating End-to-End Learning Viability
Case context: You are the lead ML engineer at a startup. The CEO recently read that end-to-end learning is highly successful and wants to deploy a pure end-to-end system for a novel task mapping complex sensory inputs to control outputs. Currently, your company has almost no labeled data pairing these specific inputs and outputs.
Question: Based on the principles in Machine Learning Yearning, what should you advise the CEO regarding this pure end-to-end approach, and what is the primary justification?
Sample answer: I would advise the CEO to approach the end-to-end learning strategy with great caution. End-to-end systems are typically only successful when there is an abundance of labeled data available for both the input and output ends. Because we currently lack a large dataset of these paired inputs and outputs, a pure end-to-end system will be exceedingly difficult to train.
Key points:
- Advise approaching with great caution
- End-to-end learning requires abundant labeled input-output data
- The system will be difficult to train without this paired data
Rubric: 1 point for advising to approach with great caution. 1 point for explaining that end-to-end systems need abundant labeled data for both ends. 1 point for stating that the lack of this data makes training difficult.
0
1
References
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Tags
Machine Learning
Deep Learning
Supervised Learning
Dive into Deep Learning @ D2L
Data Science
Machine Learning Strategy
Machine Learning Yearning @ DeepLearning.AI
Related
What type of labeled data pairs does a pure end-to-end autonomous driving system require for training?
End-to-end learning systems are not always a good choice, even when they can be remarkably successful with abundant data.
To train a pure end-to-end autonomous driving system, you need a large dataset of (Image, _____) pairs.
Match each end-to-end learning domain to the specific labeled input-output data pairs required to train it.
Order the causal chain explaining why a pure end-to-end autonomous driving system is difficult to train.
Why does collecting training data for a pure end-to-end autonomous driving system require specially instrumented cars?
End-to-end learning systems tend to perform well when large amounts of labeled data exist for both the input end and the output end.
When sufficient labeled input-output data is not available, you should approach end-to-end learning with great _____.
Match each data collection challenge for end-to-end autonomous driving to the consequence described in Machine Learning Yearning.
Order the reasoning steps a practitioner should follow when evaluating whether to use a pure end-to-end approach for a new problem.
Analyzing Data Requirements for End-to-End Systems
Evaluating End-to-End Learning Viability
Resource Requirements for Autonomous Data Collection