[Day 120] Starting Stanford's CS246: Mining Massive Datasets + MIT's Intro DL

 Hello :)
Today is Day 120!


A quick summary of today:


Last night I saw a notification that MIT is going to livestream their first intro to DL lecture on youtube (from their 2024) course, and this morning I decided to check what it's about. This is the official website, and it will provide lectures + homeworks. The course lectures will go from 29th April to 24th June. And the schedule is:

As a 'basics lover' I am excited to go over old and hopefully new material. I am excited to see MIT's take on teaching intro to DL. 


The summary of the 1st lecture is bellow

It started it where DL fits with AI and ML.

Gave a general and very well put (as expected for MIT) explanation of a neuron/perceptron
Provided an example of a simple neural network
Also, how does the network know how wrong it is? Thanks to the loss

However, using the whole dataset to update the weights W (Gradient Descent) might not be the best idea, especially with the amount of data available these days. That is where Stochastic Gradient Descent comes in.
In the end, we got introduced to the 2 of the most common regularization techniques: dropout, early stopping. 

As for the CS246: Mining massive datasets

It was on my list for a while, the reason I did not start it earlier was because I was not sure if there were videos on it (even if there were not, I would still end up doing it, but a video lectures just adds a little more to just reading slides/book chapters). I saw today that there are lecture videos from winter 2019. Yes it was 4 years ago, but I compared slides from the most recent release (winter 2024) with the slides from winter 2019 and there is little deviation towards the end, when I can just watch the lecture and then by myself read the slides. 

Today I covered lecture 1

Covered topics:

MapReduce, Spark, Spark's RDD, cost measures



I also registered for a new event hosted by Global AI for good that's in collaboration with Oxford University - MLx Generatie AI (Theory, Agents, Products) on 22-24th August 2024. ^^

Topics to be covered:

  • Advanced theoretical topics in representation learning (e.g., vision, language, multi-modal, …)
  • Agentic AI (e.g., agentic reasoning and design patterns)
  • Human+AI alignment
  • Building Gen. AI products — from model.fit() to market.fit()
  • Using SOTA foundation models (e.g., fine tuning, RAG, RLHF, prompt engineering, …)
  • Application of large frontier models in applied domains (e.g., medicine, finance, education, …)


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