Learning with not Enough Data Part 2: Active Learning
Active Learning is a technique used in machine learning when there's not enough labeled data for training. It involves selectively asking humans to label certain examples, rather than labeling all of them. This approach helps reduce the cost and time required for human labeling while still achieving good model performance.
Active Learning is a technique used in machine learning when there's not enough labeled data for training. It involves selectively asking humans to label certain examples, rather than labeling all of them. This approach helps reduce the cost and time required for human labeling while still achieving good model performance.
---
Why it matters: This matters because many real-world problems have limited labeled data, making it difficult to train accurate models. Active Learning provides a way to overcome this challenge by efficiently using human resources.
Source: https://lilianweng.github.io/posts/2022-02-20-active-learning/
This article was originally published at: https://lilianweng.github.io/posts/2022-02-20-active-learning/