arisuchan    [ tech / cult / art ]   [ λ / Δ ]   [ psy ]   [ ru ]   [ random ]   [ meta ]   [ all ]    info / stickers     temporarily disabledtemporarily disabled

/λ/ - programming

structure and interpretation of computer programs.
Name
Email
Subject
Comment

formatting options

File
Password (For file deletion.)

Help me fix this shit. https://archive.arisuchan.jp/q/res/2703.html#2703

Kalyx ######


File: 1504272543539.jpg (37.62 KB, 306x306, artificial-intelligence.jpg)

 No.582

 No.584

>>582
Some things I forgot (Too many resources):

For datasets : https://www.kaggle.com/

Easy machine learning project you can do with K nearest neighbors and the iris dataset: https://machinelearningmastery.com/machine-learning-in-python-step-by-step/

 No.585

>>582

My favourite Artificial Intelligence course,
https://www.edx.org/course/artificial-intelligence-ai-columbiax-csmm-101x-1

It's challenging and well explained.
You'll learn search algorithms, A, bfs, dfs, idfs, ida and more

 No.586


 No.587

File: 1504295890674.jpg (2.48 MB, 3600x2700, Renstorm Robot.jpg)

Interesting channel on Twitch.tv:
https://www.twitch.tv/serpent_ai
>The channel's content all gravitates around one central project: The Serpent framework. Built entirely live on stream, it aims to facilitate the creation of game agents & AIs that are able to interact with video games. You will get to see the development of the framework itself as well as agents for many popular games.

 No.811

https://fossbytes.com/google-automl-defeats-human-wrote-better-code/
Isn't this just hyperparameter tuning? I can't find anything about it actually writing code.

 No.812

you guys dont really pay for these courses do you? I thought we all appreciated free info here?

 No.813

>>812
there are plenty of free resources available.

 No.1278

As a visual learner, I personally think that Ng's coursera is the best intro. Having the schedule and assignments also helps motivate you to finish it.

If you're interested in getting a better idea of what is involved in ML, I recommend checking out the blogposts on kaggle written by the competition winners— http://blog.kaggle.com/category/winners-interviews/ I forget which article it was that I liked a lot, but it was basically two statisticians working at healthcare companies that won, and talked about what led them to choose their model, and how it works.

If you want to take the SICP-esque approach, the bible of ML is ESLR (not in a meme-sense like SICP), but I recommend starting with ISLR. Yes, it takes 30 more pages to reach linear regression, and doesn't cover neural nets as in-depth as its older brother does (nobody reads ESLR for DNNs anyway), but the math is a better pace. Plus, as someone who primarily uses Python, it was neat to see how R works.

It's free here: http://www-bcf.usc.edu/~gareth/ISL/

 No.1397

Guys i want to start machine learning but what should one learn before starting it? I think it might be exhausting to directly start to learn ML.

 No.1399

http://libgen.io/book/index.php?md5=C37CE53726FB431E5815F9B1E573BFD6

I do not know what I am talking about.
Figured I'd say that before I go recommending things.
I'm taking an intro to AI course right now and this is the book we're using. I love it. I think you should read through most of this and try to implement some of the algorithms. The pseudocode is in there and it's pretty clear. I'm taking a ML course next semester but at the end of this intro to AI course my prof said he would get into ML for about a week at the end. The fact that he said that we'd get to it at the end probably means that I should know the intro stuff before I learn the ML. Hope this helps.

 No.1410

>>1397
I'm planning on starting ML too
I would think some linear algebra, data science, statistics, and Python( or R i guess) would be prerequisites?
But I haven't actually learnt anything yet so I dunno

 No.1581


>>1410
Actually i suppose that python is best choise for machine learning, as making code in it is really fast, what is more, you shouldn't spend much time on linear algebra because its like a black box, what will be more better for you is focusing on some basic things and understanding statistic and plot of machine learning. After that you can take some advance steps to learning neural networks and choosing a kind of speciality (like computer vision engineer)

 No.1749

>>1581
>you shouldn't spend much time on linear algebra because its like a black box
depends on what your learning objectives are.

If you want to really deeply understand what is going on from a theoretical perspective, linear algebra is a must because it is so crucial.

If you want to get started actually making AI's right away, you can skip it I guess but you'll just be gluing together other peoples' work.



[Return] [Go to top] [ Catalog ] [Post a Reply]
Delete Post [ ]