본문 바로가기

Data-science/논문 읽기

ablation study가 뭐냐 대체...

반응형
  • An LSTM has 4 gates: feature, input, output, forget. We might ask: are all 4 necessary? What if I remove one? Indeed, lots of experimentation has gone into LSTM variants, the GRU being a notable example (which is simpler).
  • If certain tricks are used to get an algorithm to work, it’s useful to know whether the algorithm is robust to removing these tricks. For example, DeepMind’s original DQN paper reports using (1) only periodically updating the reference network and (2) using a replay buffer rather than updating online. It’s very useful for the research community to know that both these tricks are necessary, in order to build on top of these results.
  • If an algorithm is a modification of a previous work, and has multiple differences, researchers want to know what the key difference is.
  • Simpler is better (inductive prior towards simpler model classes). If you can get the same performance with two models, prefer the simpler one.

 

An ablation study typically refers to removing some “feature” of the model or algorithm, and seeing how that affects performance.

 

모델이나 알고리즘의 특징들을 제거하면서 그게 퍼포먼스에 어떤 영향을 줄지 연구하는 거

 

https://www.quora.com/In-the-context-of-deep-learning-what-is-an-ablation-study

 

In the context of deep learning, what is an ablation study?

Answer (1 of 3): An ablation study typically refers to removing some “feature” of the model or algorithm, and seeing how that affects performance. Examples: * An LSTM has 4 gates: feature, input, output, forget. We might ask: are all 4 necessary? What if I

www.quora.com

For instance,

Ablation studies by digitally removing whole fish or parts of the fish from the images revealed that the classifier learned discriminative features from the image foreground, and we observed that the deformations of the head region, rather than the visually apparent bent tail, were more important for good classification performance

Deep Fish - Sep 09, 2016

or

we ablated (i.e. removed) some of the repeated elements to see if the DNN confidence score for that image drops. Psychologists use the same ablation technique to learn which image features humans use to recognize objects

Nguyen_Deep_Neural_Networks_2015_CVPR_paper.pdf

반응형