Case Study

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

Updated 2026-05-27

Contributors are:

Who are from:

Tags

Machine Learning

Deep Learning

Supervised Learning

Dive into Deep Learning @ D2L

Data Science

Machine Learning Strategy

Machine Learning Yearning @ DeepLearning.AI