[Day 65] Stanford CS224N (NLP with DL): Multimodal DL and Model analysis and explanation

 Hello :)
Today is Day 65!


A quick summary of today, finalising the last parts of CS224N - NLP with DL by Stanford University
  • (just watched) Lecture 18 and 19: Future of NLP and Model Interpretability & Editing

First I will share my notes, and then just a quick summary and thoughts on the course.

Lecture 16: Multimodal deep learning

I got a lot of research papers to read from this lecture. Two are:
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale; and Learning Transferable Visual Models From Natural Language Supervision.

Lecture 17: Model analysis and explanation


Quick summary and thoughts on the course

I wrote a lot of notes, and I am glad - writing something down with my hand definitely helps me remember it better.

Definitely a very comprehensive course and high quality, and I am glad I decided to commit to doing it. Going back to the start of NLP, through human languages > word vectors > word2vec > seq2seq > RNNs > LSTMs > Transformers, but also learning code generation, natural language generation, how LLMs word - pretraining, finetuning, evaluation metrics. Amazing.  

Maybe someday I might pay for the XCS224N if I have the money, so that I can see lectures about *current* advances in the field. But this course (half of which was from 2021, half from 2023) definitely helped me create a sturd base for my future NLP journey. Thank you to Professor Chris Manning and head TA John Hewitt - they were top-notch ^^


That is all for today!

See you tomorrow :)

Popular posts from this blog

[Day 198] Transactions Data Streaming Pipeline Porject [v1 completed]

Image
 Hello :) Today is Day 198! A quick summary of today: data streaming pipeline project [v1 done] Here is a link to the project's repo. Well ... I did not know I can do it in a day (~14 hours) after yesterday's issues but here we are. Turns out in order to insert the full (~70 variables with nested/list structure), I need the proper pyspark schema. And yesterday I did not have that and that is why when I was reading data in the kafka producer I was getting NULL in the columns - my schema was wrong. Well today I not only fixed the schema for the 4 variables I had yesterday, but included *all* the variables that come from the Stripe API ~ 70 (for completeness).  When I run docker-compose, the data streams and is input into the postgres db (and is still running). Unfortunately, the free Stripe API for creating realistic transactions has a limit of 25, so every 3 seconds, 25 new transactions are sent to the db. It has been running half the day (since I got that set up) and as I am wr
Read more

[Day 107] Transforming natural language to charts

Image
 Hello :) Today is Day 107! A quick summary of today: created text2chart - transforming natural language to charts [ github ] [ webapp ] I am super sick, but in the around 3 hours of my fever not being high, I managed to study a bit. I was again thinking about creating some nlp project but was stuck on the idea of how to host a model. After looking around I found this article where they create a similar app called chat2vis  and they use codellama. I know codellama is an open source model that I can get from huggingface and I wondered, how did they host it. Turns out - they ask the user to input a huggingface api key, which then allows for querying and generating content. (AWESOME! this is applicable to some of the other PDF chat apps that I have, but I will look to make an app of them later).  My fever eased a bit, and I sat on my chair to do some work ^^ Here is a breakdown of the app. I used streamlit. Also, 2 default datasets during dev: Financial Statements of Major Companies(2009-
Read more

[Day 54] I became a backprop ninja! (woohoo)

Image
 Hello :) Today is Day 54! A quick summary of today: Read through cs231n's neural network lectures [1] [2] [3] Spent 8 hours going over Andrej Karpathy's backprop ninja tutorial After yesterday's confidence boost in doing backprop, I came in today with the intention of becoming of, as Andrej Karpathy calls it, a backprop ninja.  The cs231n NN lectures were the usual about how NN became to be, param initialization, activation functions, loss functions, regularization and optimizers. Nothing out of the ordinary, but still was good to reassure myself of that knowledge. But that was definitely not the main even of today. As I mentioned, I wanted to become (or at least attempt to become) a backprop ninja today. I have watched that particular tutorial twice, the 1st time I had no idea what is going on, the 2nd time I could follow, and now it was the 3rd time - and now, I wanted to participate and actually see the why and the how of the things we have to do, when we do manual back
Read more