A large part of the success of supervised machine learning systems is the existence of large quantities of labeled data. Unfortunately, in many cases, creating these labels is difficult, expensive, and time-consuming.

An obvious solution is to use machine learning to aid in the creation of the labels, but this presents a chicken and egg problem: how do we build a model to create labels before labeling our data to train that model?

Active Learning is one solution. A semi-supervised learning technique to build better-performing machine learning models using fewer training labels.

Paper mentioned in the video:
Active Learning Literature Survey. [ Ссылка ]

🔔 Subscribe for more stories: [ Ссылка ]

📚 My 3 favorite Machine Learning books:
• Deep Learning With Python, Second Edition — [ Ссылка ]
• Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow — [ Ссылка ]
• Machine Learning with PyTorch and Scikit-Learn — [ Ссылка ]

Twitter: [ Ссылка ]

Disclaimer: Some of the links included in this description are affiliate links where I'll earn a small commission if you purchase something. There's no cost to you.

свернуть