When Richard Feynman explained the difference between “knowing something” and “knowing the name of something”, he presented his secret formula for effective learning. The trick was simple. When you learn a new concept and want to build a ground-up understanding of it, simply teach it to a child, review it, organize and simplify and then transmit it.

So, I am excited to try the Feynman technique and write a weekly blog post on the most interesting things I have learned during the week. There is a deluge of resources on data science and I often find myself dabbling in exploring data science blog posts, videos, and podcasts and have a hard time remembering the things I have learned.

However, lately, I have realized that writing gives me closure and helps me demystify complicated concepts. In my blog posts, I generally talk about a new thing I have learned during the week, followed by a small coding exercise and in the end, I share a useful thought of the week which I have somehow discovered serendipitously while "scrounging around in my life for things to improve". These are just informal, mini episodes summarizing my readings/research/reflections. Feel free to make them richer with relevant comments and feedback. Happy reading!

Latest Posts

• Episode 1: Multi-output forecasting

  This week I read the paper “Deep Multi-Output Forecasting - Learning to Accurately Predict Blood Glucose Trajectories” [2], and this is everything I learned from it:

• Episode 2: seq2seq Models

  This week I listened to a podcast on “seq2seq models” on Data Skeptic [1], and this is everything I learned from it:

• Episode 3: People are Not Guinea Pigs!

  This week I read an article, “People are not problems” [1] by Erik Johnston and Jessica Givens, and it took me on a reading spree as I hopped from one hyperlink to another.

• Episode 4: Book Review (Part I): Dataclysm: Who We Are (When We Think No One's Looking) by Christian Rudder

  This week I read the book, “Dataclysm - Who We Are (When We Think No One’s Looking)” [1] by Christian Rudder, and this is everything I want to remember from it.

• Episode 5: Deep Learning by Ian Goodfellow, Yoshua Bengio and Aaron Courville

  This week I read the first few chapters of the book, “Deep Learning” [1] by Ian Goodfellow, Yoshua Bengio and Aaron Courville, and this is everything I want to remember from it. (The book is available online [1] for free!)

• Episode 6: What in the world is Kullback-Leibler Divergence?

  This week I discovered a new blog on topics related to Bayesian Theory and this is everything I would like to remember from a post related to Kullback-Leibler Divergence.

• Episode 7: Demystifying the buzz words in Big Data

  This week I made the following notes while taking the “Big Data Essentials: HDFS, MapReduce and Spark RDD” course on Coursera [1].

• Episode 8: ML Notes (Part I): Fundamentals of Machine Learning Theory

  These days I am reading the book “Machine Learning” by Tom M. Mitchell and I will be documenting some important concepts from its chapters in a series of blog posts.

• Episode 9: ML Notes (Part II): Fundamentals of Decision Tree Theory

  These days I am reading the book “Machine Learning” by Tom M. Mitchell and I will be documenting some important concepts from its chapters in a series of blog posts.

• Episode 10: Notes from Deep Learning Course (Part I)

  This is part of a series of posts on some of my notes from course on Deep Learning taught by Prof. Yann LeCunn at NYU in Spring 2020 [1].

• Episode 11: Notes from Machine Learning Specialization by Andrew Ng

  This is part of a series of posts on some of my notes from course on Machine Learning Specialization taught by Prof. Andrew Ng.

• Episode 12: Inferential Statistics and Hypothesis Testing Playbook

  This post acts as a handy cheat sheet on how to draw important inferences from a given dataset using statistics and hypothesis testing.

• Episode 13: Important Notes on Linear Regression

  Linear regression is about modeling the linear approximation of the causal relationship between two or more variables.

• Episode 14: Week 1 of Building Multi-Agent Applications - A Bootcamp

  I have recently joined a mentorship program for building Multi-Agent LLM Applications and will be sharing my learnings in a series of detailed blog posts over the next couple of weeks.

• Episode 15: Week 2 of Building Multi-Agent Applications - A Bootcamp

  I have recently joined a mentorship program for building Multi-Agent LLM Applications and will be sharing my learnings in a series of detailed blog posts over the next couple of weeks.

• Episode 16: DeepSeek - Understanding the basics

  I have recently joined a mentorship program for building Multi-Agent LLM Applications and will be sharing my learnings in a series of detailed blog posts over the next couple of weeks.