Скачать или смотреть Probing Classifiers: A Gentle Intro (Explainable AI for Deep Learning)

Probing Classifiers are an Explainable AI tool used to make sense of the representations that deep neural networks learn for their inputs. They allow us to understand if the numeric representation at the end (or in the middle) of the model encodes certain properties of the input which we are interested in (for example, whether an input token is a verb or a noun). Using probes, machine learning researchers gained a better understanding of the difference between models and between the various layers of a single model.

Introductions (0:00)
Motivation for probes in Machine Translation (0:40)
Probing sentence encoders (3:42)
How a probe is trained (5:32)
Probing token representations (8:08)
Size of probes (9:15)
Better metrics using Control Tasks (9:48)
Conclusion (10:32)

Explainable AI Cheat Sheet: https://ex.pegg.io/
1) Explainable AI Intro :    • Explainable AI Cheat Sheet - Five Key Cate...  
2) Neural Activations & Dataset Examples    • Neural Activations & Dataset Examples  


-----

What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties
https://www.aclweb.org/anthology/P18-...

Diagnostic classifiers: revealing how neural networks process hierarchical structure
http://ceur-ws.org/Vol-1773/CoCoNIPS_...

Designing and Interpreting Probes with Control Tasks
https://www.aclweb.org/anthology/D19-...

Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
https://arxiv.org/abs/1608.04207

What do you learn from context? Probing for sentence structure in contextualized word representations
https://arxiv.org/abs/1905.06316

-----


Twitter:   / jayalammar  
Blog: https://jalammar.github.io/
Mailing List: https://jayalammar.substack.com/

------

More videos by Jay:

The Narrated Transformer Language Model
   • The Narrated Transformer Language Model  

Jay's Visual Intro to AI
   • Jay's Visual Intro to AI  

How GPT-3 Works - Easily Explained with Animations
   • How GPT3 Works - Easily Explained with Ani...  

Up and Down the Ladder of Abstraction [interactive article by Bret Victor, 2011]
   • Up and Down the Ladder of Abstraction [int...  

The Unreasonable Effectiveness of RNNs (Article and Visualization Commentary) [2015 article]
   • The Unreasonable Effectiveness of RNNs (Ar...