50+ days of Machine Learning

 Hello :) Today is Day 120! A quick summary of today: started MIT's Intro to deep learning  2024 course started Stanford's CS246: Mining massive datasets 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 (Gr

 Hello :) Today is Day 119! A quick summary of today: read Learning the Graphical Structure of Electronic Health Records with Graph Convolutional Transformer by Choi et al. (2020) saw: Four Ways of Thinking: Statistical, Interactive, Chaotic and Complex - David Sumpter ( youtube ) I learned about Graph Transformers on Day 110  and I had saved this paper from Professor Choi and wanted to read it for a while. Firstly, I wrote some summary notes of  it . One, it involves the usage of graphs, and two - Professor Edward Choi wrote it (I studied some of his lectures on  intro to AI ) Studying electronic healthcare records (EHR) using deep learning can help in various tasks, including predicting diagnosis, learning medical ceoncept representations, and making interpretable predictions. EHR data is often store as hierarchical graphs as in the picture. The common way to to process this data is to consider each encounter as an unordered set of features which does not care about its graphical str

 Hello :) Today is Day 118! A quick summary of today: - received info on OxML: Fundamentals - reviewed interestung books on manning.com - attended a career event in Yonsei university - invited to do a talk about text 2 chart in an online Stanford event Firstly, a few months ago I applied and got accepted to attend an online ML summer school organised between AI for global good and Oxford university. Above is the schedule for the 4-day classes. Plus there are 2 networking sessions. The sessions are live and in Korea the above times are between 9pm and 3am. Even though the sessions are going to be recorded, I will attend them live so that I can ask questions on the spot if needed.  Secondly, during my bus ride to Seoul I started looking for an interesting book to read on manning.com and I think I found some good candidates worth reading.  I had a look at a few books, but the above looked the most interesting. Also, among them are 2 project type items w

 Hello :) Today is Day 117! A quick summary of today: watched a couple of 3brown1blue 's vides transferred more posts to the new blog Firstly, I watched this one about abstract vector spaces In abstract vector spaces we are dealing with a space that exists independently from the coordinates we are given. and the coordinates can be arbitrary depending what we choose as our basis vector. Determinants and eigenvectors dont care about the coordinate system - the determinant tells us how a transformation sclaes areas, and eigenvectors are the ones that stay on their own span during a transformation. Se can change the coordinate system, and it wont affect the values of the above 2. Functions also have vector-ish qualities. in the same we can add 2 vectors together, we can add 2 functions to get a third, resulting function. It is similar to adding vectors coordinate by coordinate. Similarly, we can scale a function. and it is the same as scaling a vector by a number What does it mean for