< change language
After watching this video from Siraj Raval, I decided to jump right on board of the #100daysofMLcode initiative! (even though I am something like 73 days late...) The goal here is to devote (at least) 1h every day, for the next 100 days, to studying ML or writing code!
According to the rules posted by Siraj, I must:
Are you into #100DaysofMLCode as well? Let me know in the comments what you have been doing!
According to the rules posted by Siraj, I must:
- Make a public pledge for this, which this post is;
- Make a log of everything, which this post will also be;
- Whenever I see something related to this #100DaysofMLCode, be supportive!
Progress log
For the day 0 I wrote this post and spent quite some time thinking about what I will do throughout. I am thinking of studying several topics about ML and then writing educative posts here, for the blog.- For today I wrote this twitter proof, tackling a mathematical property of neural networks with linear activation functions.
- Started reading about Reinforcement Learning and Markov Decision Processes; already imagined a nice example I will be using when writing about this... it will involve cake, lemonade and eventually a stomach ache.
- I have been reading more about MDPs, and I found this answer on Cross Validated specially enlightening.
- Reading more about the functioning of MDPs in this blog (which seems to have taken inspiration from these slides for this particular blog post).
- Kept reading the resources from above; started sketching an example MDP to be used in my next blog post.
- Finished sketching the example MDP and did some calculations related to it; started writing the first blog post about this and created a representation of the MDP for the post.
- Finished writing and published this post on the basics of Markov Decision Processes.
- Started writing the second post on MDPs, where we will explore how the changes in γ and the transition probabilities affect the policies.
- I wrote another post on MDPs, this time about the discount factor γ.
- Following up on the last post, I wrote here about how the optimal policy can change when the discount factor changes.
- Decided to use the Hanoi Towers as a model problem and started encoding it as an MDP; wrote some helper code for that and you can find such code here.
- Kept writing the code from the previous day and applied the algorithm of value iteration to the Hanoi Towers, solving them. The code is in this GitHub repo.
- Wrote this post on how to encode the problem of the Tower of Hanoi into an MDP.
- Wrote the code for the policy iteration algorithm to solve the Tower of Hanoi; the code is in my GitHub.
- Today I tried implementing Q-learning to solve the Tower of Hanoi. It isn't learning properly yet, so I decided not to upload the code to GitHub.
- For today I have been all over the internet to try and find the reason why my Q-learning algorithm isn't working... Still haven't succeeded.
- Because Q-learning wasn't working I tried to implement double Q-learning, just to be sure my problem wasn't one of bias. At first double Q-learning wasn't working as well, but now both algorithms are working just fine! They have been uploaded to GitHub now.
- Started writing a Python notebook where I will explain the algorithms and show how to use them to solve the Tower of Hanoi. Those explanations will also be put here in the blog as they are written. The notebook can be found in my GitHub as well.
- Kept on working on the notebook! Practically finished the section on value iteration.
- I had to stop a bit; sorry for that! I am back and I have been reading about ML on financial markets and have been taking an online course about data science. It isn't exactly the same as ML, but knowing how to handle data ought to make me better at ML, right?
- Kept taking the course Data Science: Visualization on edX.
- Today I read about using machine learning for text translation.
- Advanced a lot in one of the modules of the Data Science course...
- And today I finished it!
- I started the module on probability...
- And today I kept going...
- And finished it today!
- Today I resumed my work on the Hanoi RL notebook.
- Wrote about Q-learning and double Q-learning on my notebook.
- Started the new module of the Data Science course.
- Kept learning!
- Today I kept learning for the course I am taking.
- ...
- ...
- ...
- ...
- ...
- ...
- ...
- ...
- For the past days I have been studying for my online course... I think I have done around 2/3 of the course by now.
Are you into #100DaysofMLCode as well? Let me know in the comments what you have been doing!
- RGS
Pledging to do 100 days of Machine Learning and progress log!
Reviewed by Unknown
on
September 17, 2018
Rating:

No comments: