Learn Before
End-to-End Learning Needs Abundant Labeled Input-Output Data
In the autonomous-driving example, a pure end-to-end approach would need a large dataset of image and steering-direction pairs. Collecting such data is time-consuming and expensive because it would require specially instrumented cars and a huge amount of driving to cover a wide range of scenarios, making the end-to-end system difficult to train.
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
Related
End-to-End Sentiment Classification
End-to-End Speech Recognition
End-to-End Autonomous Driving Skepticism
End-to-End Learning Needs Abundant Labeled Input-Output Data
Large End-to-End Neural Networks Can Avoid Representation Limits
Directly Learning Rich Outputs
What structure does end-to-end learning typically replace in a machine learning system?
Neural networks are commonly used in end-to-end learning systems.
The term 'end-to-end' refers to the learning algorithm going directly from the _____ to the desired output.
Match each output type to its description as an example of what end-to-end deep learning can produce.
Order the steps of an end-to-end sentiment classification system as described in Machine Learning Yearning.
Given the right labeled input-output pairs, what can end-to-end deep learning sometimes produce as output?
End-to-end deep learning is limited to producing outputs that are a single number.
End-to-end deep learning is an accelerating trend that allows directly learning _____ that are much more complex than a number.
Match each end-to-end learning concept to its definition from Machine Learning Yearning.
Order the reasoning steps that explain how end-to-end deep learning enables rich outputs beyond a single number.
Learn After
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.