Главная
Study mode:
on
1
Intro
2
Why pretraining
3
Satellite Remote Sensing
4
Fine Tuning Pretrained Models
5
Comparing Two Methods of Fine Tuning
6
Empirical Observations
7
Linear probing
8
Finetuning
9
Regularizers
10
Linear Probe
11
Questions
12
Discussion
13
In Context Learning
14
Whats Happening Here
15
Mental Model
16
Latent Concept
17
Problem Distribution
Description:
Explore the intricacies of utilizing pre-trained models in this guest lecture by Aditi Raghunathan for CMU's Advanced NLP course. Delve into the reasons behind pretraining, examine satellite remote sensing applications, and compare different fine-tuning methods. Investigate empirical observations, linear probing techniques, and various regularizers. Engage with in-context learning concepts, develop mental models, and understand latent concepts and problem distributions. Participate in a thought-provoking discussion and question session to deepen your understanding of advanced natural language processing techniques.

CMU Advanced NLP: How to Use Pre-Trained Models

Graham Neubig
Add to list