Recently on Twitter, I ran a quick poll to understand if people are fascinated by causality and the response was quite overwhelming.
Results: 44/45 people voted interested, to see what I have to say.
So, I will be doing one daily bullet point list on Twitter on Causality starting with The Book of Why for many reasons-
- It is one of the latest, beginner level books on the topic thus easily comprehensible and up-to-date.
- Causality, according to me, is one of the most important topics in the study of artificial intelligence and an excellent tool in the quest for the imitation of human intelligence.
- The book has been penned by no other than Judea (Pearl), who I greatly admire and owe a lot to for taking such an immense leap of faith in me, as my mentor and for training me to trust my own intuitions.
- Causality has not yet been studied widely – in combination with other theories of machine intelligence, namely information theory, deep learning, probabilistic inference, associative memory etc. which I intend to change.
- I personally couldn’t find any unbiased critical analysis of Judea’s work. While there are a few interesting rebuttals of his work by Nancy Kreiger, Rubin and some other academics in general. But in my opinion, while some of them lack common decency expected from grown-up communications, many criticisms are simply non-constructive.
- Among non-academics, the two other groups I come across online, are either complete believers or abandoners. However, there is a third type that is much needed – the ones who can question his work in a constructive manner and build on top of it.
- Any editor will tell you how hard is it to convince an author to throw away a major proportion of his work. Liz Gilbert among others has often talked about having a nurturing detachment to your work. It is because of this I believe it’s incredibly important to study and review Judea’s work, from the most respectful and caring place possible.
- Thus, the goal of this exercise is – first, to learn more about his work among that of others in causality and secondly, to review his work and dismantle it and pick the true gems and rebuild the rest.
To sum it up, I strongly believe Geoffrey Hinton’s statement applies to almost every tool, technique and method we know of in science and esp more so in artificial intelligence. Let us start once again from the whiteboard…
Some quick notes:
- My daily notes which contain my top highlights will be bullet listed on Twitter.
- A detailed commentary of the book chapters will be done here on the blog, not necessarily on a daily basis
- All the bullet lists along with the commentary will be compiled into a google doc, later available for quick download
- Also, the entire series will be catalogued so you don’t miss anything.
On a final note,
It is often incredibly hard for my pen to match the velocity of my head thus I can sometimes jumble up my sentences and leave many grammatical errors. Therefore, I would like to apologize for that in advance and express my deepest gratitude for your patience with my very human shortcomings.