고정된 트윗
TK • 木下
7K posts
TK • 木下
@wordsofteekay
coding . ml . math . writing . books . https://t.co/SJXxlX5JeT
🇯🇵⇄🇧🇷 가입일 Aralık 2009
316 팔로잉9.7K 팔로워
@Aryakris_20 I'm glad you enjoyed it! If you have any suggestions other than what I mentioned in the article, lmk.
English
@wordsofteekay I just went through your AI/ML for bio learning path and it is so well written. Thanks for this!
English
[ML Grind]
Focusing on foundation work:
> Deep Learning/LLM/ML foundation studies
> Bio x AI research: unwrapping AlphaFold
> Finished the Machine Learning System Design book
Documenting everything in my physical notebook and the ML research repo: github.com/imteekay/machi…
English
So many books, so little time.
Besides The Art of Doing Science and Engineering, I'm excited to read Sutskever's List and The Infinity Machine, a book released a couple of days ago.
Time to remove all distractions and focus.
TK • 木下@wordsofteekay
📚 Started a new book today. I'm on the first few pages, and the way it was written already caught my attention. "Teachers should prepare the student for the student's future, not for the teacher's past. Most teachers rarely discuss the important topic of the future of their field, and when this is pointed out, they usually reply: 'No one can know the future'. It seems to me the difficulty of knowing the future does not absolve the teacher from seriously trying to help the student to be ready for it when it comes." Excited to be educated on styles of learning and thinking, and then get back to training, applying those principles.
English
2 years ago, I started learning ML for fun, and then, after learning more about Hamming's ideas, I decided to take it seriously to accomplish my life's big goals.
I'm still in the process, but starting to get the rewards and making progress.
→ post my ML learning experience: iamtk.co/my-experience-…
→ post about my learning roadmap: iamtk.co/ai-ml-for-biol…
There is so much to learn, still.
English
After 12 years working as a software engineer, last month I decided to take a new adventure in my career and accepted a Machine Learning Engineer role. It's been a month since I've been working on data science and ML problems.
The struggle of my 'knowledge gap' fires my curiosity and keeps me alive. It's been quite some time since I've felt this excited.
It's been a fun and exciting month. I should write about that.
English
@plutohsin I'm not really sure. I actually don't schedule time to read, I just pick up the book whenever I have time. A bit 'chaotic' but it works well for me.
English
@wordsofteekay How many pages do you read in a day? That’s honestly really inspiring.
English
📚 Started a new book today.
I'm on the first few pages, and the way it was written already caught my attention.
"Teachers should prepare the student for the student's future, not for the teacher's past. Most teachers rarely discuss the important topic of the future of their field, and when this is pointed out, they usually reply: 'No one can know the future'. It seems to me the difficulty of knowing the future does not absolve the teacher from seriously trying to help the student to be ready for it when it comes."
Excited to be educated on styles of learning and thinking, and then get back to training, applying those principles.
English
I know that people like notebooks and pens, but imho they are missing the point here: the post is not about the 'tool' per se, it is more about how to use the 'tool' to augment your thinking.
---
But to answer the questions: the video notebook is a moleskine and the 10 new ones are non-branded. The pen I got as a gift from a small Japanese mall owner.
English
Just bought 10 more new notebooks to augment my thinking. Let's keep learning.
TK • 木下@wordsofteekay
Almost finishing a notebook I bought at Sekaido in Shinjuku, Japan. Full of notes: study notes, math problems, journaling.
English
📝 I hope with this new post, you can steal some ideas, and insights, and put them into practice in your life. This is my reflection about reading 47 books in the first 6 months of 2023 and how I am focusing on reading less + applying them in my life.
iamtk.co/i-read-47-book…
English
@CausalFlops28 It's an internal book club at the company I work for.
English
@eugediana @ladanuzhna "publish and watch 100s of Chinese companies pursue the same" = increase in competition, especially when you have a competitive edge ("having some incredible data").
English
@ladanuzhna Am curious what’s the downside of just publishing the way you’d prefer ?
English
I absolutely hate the state of having some incredible data that we can’t publish. Like the options are to publish some random press release with no details or to publish and watch 100s of Chinese companies pursue the same, or publish with 3-4 year lag. All of these are bad.
In general, my instinct is to share important data with the world (a rising tide lifts all boats etc), but I know that basically no other company thinks this way.
English
@silicognition David Silver's course on RL and the RL Intro book by Barto/Sutton
English
@wordsofteekay what book/course are you using for RL, if you dont mind sharing?
English
[ML Grind]
I've just finished David Silver's RL course first lecture and it's so good. Can't believe this is free.
The idea is to build a good foundation first, and then get more practical (this is why I asked about practical resources i.e. coding and projects). Let's keep going.
TK • 木下@wordsofteekay
[ML Grind] Currently studying RL through David Silver's course and using the Reinforcement Learning book as a complement. Question: does anyone recommend any other resource on applied RL? My goal is to get more practical using the ideas and intuitions from the course and book.
English
Interesting recommendations so far:
> Deep RL by Stanford: youtube.com/playlist?list=…
> Deep Reinforcement Learning in Action book: oreilly.com/library/view/d…
> Reinforcement Learning (RL) Guide by Unsloth: unsloth.ai/docs/get-start…
> Reinforcement Learning: Theory and Python Implementation: link.springer.com/book/10.1007/9…
> Papers and code: Deep Q-Learning, Policy Gradients, etc: spinningup.openai.com/en/latest/spin…
Time to lock in again.
English
[ML Grind]
Currently studying RL through David Silver's course and using the Reinforcement Learning book as a complement.
Question: does anyone recommend any other resource on applied RL? My goal is to get more practical using the ideas and intuitions from the course and book.
English