continual learning
Type: Concept
As of November 2026, continual learning has been mentioned in one podcast episode on Dwarkesh Patel (Nov 2025).
In computer science, incremental learning is a method of machine learning in which input data is continuously used to extend the existing model's knowledge i.e. to further train the model. It represents a dynamic technique of supervised learning and unsupervised learning that can be applied when training data becomes available gradually over time or its size is out of system memory limits. Algorithms that can facilitate incremental learning are known as incremental machine learning algorithms. I
| Mentioned in | 1 episode on 1 podcast (as of November 2026) |
|---|---|
| First heard | Nov 2025 on Dwarkesh Patel |
| Field | Machine Learning |
Who talks about continual learning on podcasts?
Dwarkesh Patel brought up continual learning; the most recent mention was Nov 2025 on Dwarkesh Patel.
- Ilya Sutskever – We're moving from the age of scaling to the age of research on Dwarkesh Patel (Nov 2025) — Dwarkesh Patel
What is continual learning mentioned alongside?
continual learning is most often mentioned alongside AlexNet, Neuralink and GPT-3.
Mentioned together: AlexNet, Neuralink, GPT-3, ResNet, generalization, Joshua Bengio, scaling laws, Thinking Machines Corporation, Meta, Giacomo Rizzolatti