Louis Mai

There are several files here ( https://github.com/longmaisg/Yagi ): get_yagi_data.py: scrawl data and save to CSV after each 50 pages plot_yagi.py: process data from CSV and over-write data in plot_yagi.html plot_yagi.html: show data dynamically + search box NOTE: only some pages are scrawled and shown in the html. All prompts using ChatGPT can be found here:  https://chatgpt.com/share/66edd7db-186c-800a-868a-b3e2c4097351 For Vietnamese: Data Science + Check var Chào mọi người, Trong bài viết này mình trình bày bài tập nhỏ áp dụng Data Science trong cuộc sống một cách nhẹ nhàng. Hiện tại chủ đề về ChatGPT & prompt engineer đang hot trong cộng đồng machine learning, còn chủ đề Check var cũng đang hot. Vì vậy, mình thử kết hợp prompt engineer + check var như sau: Yêu cầu ChatGPT viết code để scrawl dữ liệu danh sách ủng hộ bão lũ (Yagi). Yêu cầu ChatGPT plot danh sách này. Phần scrawl dữ liệu khá đơn giản. Tuy nhiên phần plot danh sách khá dài dòng: Đầu tiên, mình yêu cầu plot sa...

On Monday, 10 July 2023, I plan to work a bit on the technologies around ChatGPT. The technology I am talking about is Reinforcement Learning with Human Feedback (RLHF). In the simplest words, RLHF includes a policy network and a reward network. The reward network teaches the policy network by reinforcement learning. The concept of two networks is not new. Actor-Critic or Student-Teacher are some examples. The difference in ChatGPT is that, the reward network is taught by human feedback. The simple law: it is very difficult to product something, however, it is very easy to evaluate. For instance, it is so difficult to draw, but it is so easy to say which paints are more beautiful. Applying this simple law to RLHF: we the human train the reward network to know how to evaluate two summaries of an essay, while the policy network needs to learn how to generate the summaries. Then we expand to other question-answers. The new approach, RLHF, has at least two important revolutions: The summar...

This week since July 02, 2023, I plan to learn 2000 new French words in one week. Here is the summary of the project: Motivation: To escape the limbo of A2 level in French, by pouring my heart to this language. Detailed plan: accumulate new words or phrase from any source. Execution:  I follow the "grand plan" on Monday. I reach about 100 new words. I shift the plan on Tuesday, to learn by heart some French songs. Indeed, I learned by heart 3 songs. I shift again the plan on Thursday. Why? Because I found that I need to be exposed to the language (I mean, to listen to) as much as possible. So I put all effort on listening, news then later on movies. On Saturday, I added grammar and learning new vocabularies to the shifted plan. So my curriculum now is to listen to movies on Youtube while walking, and sometimes learning grammar or new words on newspapers.  Result: I would say that I have failed the project, however I have discovered the curriculum that is best suited for me. I...

If you have read the well-known book, "On Intelligence", you would agree with me that our brain is actually not a unique brain. Indeed, it is a collection of about 100,000 (one hundred thousand) mini brain. Or 100,000 mini columns as named by the author of the book. What does that mean? Our brain is a result of several levels of evolution. The first level is a part of the brain that controls basic needs such as breathe and eye movement. Sometimes we call this part the white matter. On top of the white matter, we have the so-called "gray matter", or neocortex. With neocortex, we can volunteerily control many muscles like walking and dancing. In AI, once we talk about human brain then that usually mean the neocortex. The neocortex is a thin layer, maybe about one inch. It is divided as mini-columns. There are about 100,000 mini-columns that are interconnected. Each mini column has millions of neurons (aka nerve cells in brain) and plays a role as a sub-brain. We hypot...

Nhiều người trong số chúng ta sống ở nông thôn, và trong nhà thường nuôi vài con gà. Ta có thể dễ dàng quan sát thấy sau khi gà gáy một lúc thì mặt trời bắt đầu mọc. Câu hỏi là có phải vì gà gáy nên mặt trời mới mọc không? Hay là ngược lại, vì chú gà trống biết mặt trời sắp mọc nên mới cất tiếng gáy? Không quá khó để trả lời câu hỏi này. Một cách trực quan nhất là "mặt trời nhìn có vẻ to hơn con gà. Vậy thì đúng là mặt trời tác động tới con gà rồi, chứ làm sao mà con gà có thể nhấc mặt trời lên nổi". Nếu giỏi vật lý một chút thì ta biết rằng trái đất tự xoay quanh trục nên sẽ có ngày và đêm một cách tuần hoàn, không liên quan gì tới chú gà trống. Tóm lại là mặt trời cứ mọc lên hàng ngày, còn chú gà trống có gáy hay không thì cũng không sao. Trong trường hợp này, ta nói rằng thời gian gà gáy và thời gian mặt trời mọc có liên quan với nhau (association). Và cũng có thể nói hai giá trị thời gian này có liên hệ hoặc tương quan với nhau (correlation). Lưu ý là correlation có ý ng...

         Today I try to learn new words with Visual thinking, a radical approach that basically draw everything in our mind. See this one: Can you guess what does "zeng" mean in Luxembourg? Addition? Hands? Ten? Ya, ten :) And here you are: So what does "ausgezait" mean? Oh ya, that means "to look like". Haha.

Black Swan & Antifragile (in set of Incerto) These books help me to change my mind a lot. It basically views the world in reverse compared to mainstream media. How to win friends and influence people I used to be very arrogant, easy to lose friends and not influence people. This book changed my attitude overnight. The book of Why It questions what you observe from data, and dhows that association does not mean causation. For instance, sun rises and roaster sings at the same time, but roaster cannot make the sun rises. Skip the line I know the concept of idea muscle from this book. I like the concept of the book, that the possibilities is unlimited if you practice it. 7 secrets of a happy marriage I build my marriage life around the theme provided by this book. It is the most influent book to my marry. On intelligence This book provides a solid quest towards the research of artificial intelligence, which the author calls machine intelligence. Where good ideas come from The book prov...