Concept guide · Deep learning
What is catastrophic forgetting?
A slower explanation for when the short interview answer is not enough. Start with the intuition, then connect it to the technical idea and the way an interviewer expects you to reason about it.
ML area
Deep learning → Advanced interview concept
Interview format
Advanced
Question
ML-090
Start with the idea
In simple terms
This question is asking you to explain What is catastrophic forgetting in a way that connects the idea to a real machine-learning decision. Start with the role this concept plays, then explain what changes when the data, target, or deployment situation changes.
Build the answer
How to reason about it
- 1Define the concept before naming algorithms or implementation details.
- 2Connect it to the data, target, decision, or failure mode in the question.
- 3State the assumption or evaluation check that would make the explanation trustworthy.
Go one level deeper
The technical explanation
A model can lose performance on an earlier task when it is trained on a new task, because the new updates overwrite parameters or representations useful for the old one. Mitigations include replaying old examples, regularising important parameters, adapters or parameter isolation, and multi-task objectives. The correct solution depends on whether retaining old behaviour is required. The safest way to understand this topic is to connect the definition to assumptions, data available at prediction time, the decision it supports, and how you would evaluate whether the result is useful.
Say this in the interview
A model can lose performance on an earlier task when it is trained on a new task, because the new updates overwrite parameters or representations useful for the old one. Mitigations include replaying old examples, regularising important parameters, adapters or parameter isolation, and multi-task objectives. The correct solution depends on whether retaining old behaviour is required.
Keep preparing