How to design AI from scratch?

[@matejpalm3108]

This guy Maths!

[@owonobrandon8747]

Clear and good video!

[@vojtechproschl]

Thank you!

[@gauravkhaire56]

Exactly what I needed, Thanx

[@ServedDinner]

I Really like ur videos but could u make a video about how x/y is equal to 0.x repeating except for when x=y and if y is equal to 10^n-1? Id really like to see a Video about that but ima also gonna try myself now

[@polarsingularity]

D = sqrt(2r²), as the Square can be broken up into 4 equal right triangles with short side of length r

[@SahdevSingh-io3qp]

The diagonal of square is d√2 and here 2r(2 radii of diagonal circles) is also equal to same, hence d=r√2, am I wrong somewhere?

[@zyang056]

Thanks for making this video but nothing covered here was AI or ML.

[@vojtechproschl]

Hi, This video actually contains a lot of AI concepts. We originally wanted to include a section to address this misconception but decided against it, which I now realize was a mistake. AI, at its core, is about defining goals using performance measures and optimizing algorithms to maximize or minimize the given performance measure (as we've described). There are many ways to optimize such functions, one of which is using some form of machine learning, such as neural networks, to "generate" an agent program from data. Another approach is to "design" the agent program yourself by studying the problem. This can be done through methods like search, constraint satisfaction programming, logical inference, probabilistic reasoning, and so on. A common misconception is that using "classical" approaches that don't rely on ML isn't AI, which simply isn't true. One of the reasons we created this video was to show that AI ≠ ML, and there is much more to AI than just machine learning. Hope this helps, and thank you for leaving a comment!

[@frogg03_]

​@@vojtechproschlyou don't need to call everything AI to gain traction. You clearly optimized the program iteratively yourself, not by any automated means. That is not AI, that is simply developing an algorithm and there's nothing artificial about it. You could have done so much better if you weren't just chasing buzzwords around

[@ashisdahal6145]

Great visualizations but it's too abstract. Would have loved a more in-depth implementation, preferably with code.

[@samhayzen]

The thing is any code would be extremely specific to whatever application you're talking about; you really gotta figure it out yourself based on the problem.

[@harshavardhan9399]

great video but the title is misleading. you can try something like "how do design an autonomous robot from scratch'" or something like that.

[@googleyoutubechannel8554]

Now do stairs. "Agent program"... but you repeat yourself...