NLP DUMPS

 BERT  TRANSFORMERS:

 Intuition:

https://towardsdatascience.com/transformers-explained-visually-part-1-overview-of-functionality-95a6dd460452

Implementation:

https://skimai.com/fine-tuning-bert-for-sentiment-analysis/

https://mccormickml.com/2021/06/29/combining-categorical-numerical-features-with-bert/

https://mccormickml.com/2021/06/29/combining-categorical-numerical-features-with-bert/#s3-bert-with-all-features

https://www.youtube.com/watch?v=GSt00_-0ncQ&ab_channel=PythonEngineer

ULMFIT :

Intuition:

https://blog.datascienceheroes.com/spam-detection-using-fastai-ulmfit-part-1-language-model/

https://towardsdatascience.com/understanding-language-modelling-nlp-part-1-ulmfit-b557a63a672b

https://medium.com/@j.13mehul/simplified-details-of-ulmfit-452c49294fb8

https://towardsdatascience.com/nlp-classification-with-universal-language-model-fine-tuning-ulmfit-4e1d5077372b

Implementation:

https://colab.research.google.com/drive/1fuJg9TyfsgLCzlWQ4_Etu3LJzC9Xrl8B

LR SCHEDULES:

https://towardsdatascience.com/learning-rate-schedules-and-adaptive-learning-rate-methods-for-deep-learning-2c8f433990d1

https://www.youtube.com/watch?v=81NJgoR5RfY&t=18s&ab_channel=PythonEngineer

FAISS:

Intuition:

https://towardsdatascience.com/understanding-faiss-619bb6db2d1a

https://medium.com/dotstar/understanding-faiss-part-2-79d90b1e5388

K means vs Faiss:

https://towardsdatascience.com/20x-times-faster-k-means-clustering-with-faiss-5e1681fa2654

ANN:

https://towardsdatascience.com/comprehensive-guide-to-approximate-nearest-neighbors-algorithms-8b94f057d6b6

N-GRAMS:

https://www.youtube.com/watch?v=Z-v8dKvZW0k&ab_channel=MinsukHeo%ED%97%88%EB%AF%BC%EC%84%9D

FLASK:

https://youtu.be/hAEJajltHxc