[Boards: 3 / a / aco / adv / an / asp / b / biz / c / cgl / ck / cm / co / d / diy / e / fa / fit / g / gd / gif / h / hc / his / hm / hr / i / ic / int / jp / k / lgbt / lit / m / mlp / mu / n / news / o / out / p / po / pol / qa / r / r9k / s / s4s / sci / soc / sp / t / tg / toy / trash / trv / tv / u / v / vg / vp / vr / w / wg / wsg / wsr / x / y ] [Home]
4chanarchives logo
>want to learn about machine learning, neural networks, AI
Images are sometimes not shown due to bandwidth/network limitations. Refreshing the page usually helps.

You are currently reading a thread in /sci/ - Science & Math

Thread replies: 20
Thread images: 2
File: coursera.jpg (5 KB, 250x250) Image search: [Google]
coursera.jpg
5 KB, 250x250
>want to learn about machine learning, neural networks, AI in general
>online courses make you sit through weeks worth of lectures on linear regression
>makes you do dumb shit with tiny data set using R
>"now you know AI"
>wtf
>try OpenCV courses
>literally 70% of the course is learning to draw lines on PNG files using Python
>the rest is babby's first OpenCV API call

How do I learn this shit? The materials I've found so far are just terrible.
>>
http://www.deeplearningbook.org/
>>
You're looking at the wrong courses. There are some decent ones out there if you look a bit harder.
>>
>>8121072
http://video.mit.edu/watch/artificial-intelligence-lecture-1-introduction-and-scope-26802/
>>
>>8121072
>take CS courses
>surprised that they are for retards
>>
>>8121072
http://cs231n.stanford.edu/syllabus.html
>>
>>8121072
Someone didn't realise that AI and neural networks are all glorified statistics manipulation. They work using patterns and predictions based on data, nothing more.
>>
>>8122036
Well, no shit. Thanks for clearing this up for us. Great contribution, Einstein.
>>
>>8121072
Which computer vision course are you talking about? There was one on coursera but they removed it.
>>
File: 1425650551862.jpg (16 KB, 470x581) Image search: [Google]
1425650551862.jpg
16 KB, 470x581
>>8121109
thanks!
>>
>>8121072
Try Geoffrey Hinton's neural networks course.
>>
>>8121109
this is awesome, really enjoying this lesson
>>
>>8121072
http://deeplearning.net/tutorial/

theano and tensorflow are trash, but still the best libraries/tools out there

maybe have a look at keras/caffe as well and youtube everything you dont understand

most important thing is you do the learning in Python or you are fucking retarded
>>
>>8122721
Also worth mentioning are Graphlab Create, Chainer, and Neon.

There are a bunch of framework specific courses and tutorials out there as well and you may want to look around that "awesome list" on github.
>>
>>8122724
Could you link to the awesome list on GitHub?
>>
>>8122786
There are lots of them. There's even lists of lists and lists of lists of lists and so on (the github community is quirky like that).
They're basically a big collection of resources and projects sorted by topic/programming language/framework/etc..

https://github.com/sindresorhus/awesome#computer-science
https://github.com/ChristosChristofidis/awesome-deep-learning
>>
>>8121072
Read a Modern Approach. MIT also has their lectures online.
>>
>>8121072
>literally 70% of the course is learning to draw lines on PNG files using Python
Am I stupid for thinking this sounds fun?
>>
>>8121072
>online courses make you sit through weeks worth of lectures on linear regression
ummm can't you skip lectures?
> coursera
I know there's higher level AI courses then what you looked at.
You must have taken something like Statistics for AI
>>
>>8121109
that was awesome anon!! I donĀ“t have the words to descrive how thankful i am
Thread replies: 20
Thread images: 2

banner
banner
[Boards: 3 / a / aco / adv / an / asp / b / biz / c / cgl / ck / cm / co / d / diy / e / fa / fit / g / gd / gif / h / hc / his / hm / hr / i / ic / int / jp / k / lgbt / lit / m / mlp / mu / n / news / o / out / p / po / pol / qa / r / r9k / s / s4s / sci / soc / sp / t / tg / toy / trash / trv / tv / u / v / vg / vp / vr / w / wg / wsg / wsr / x / y] [Home]

All trademarks and copyrights on this page are owned by their respective parties. Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.
If a post contains personal/copyrighted/illegal content you can contact me at [email protected] with that post and thread number and it will be removed as soon as possible.
DMCA Content Takedown via dmca.com
All images are hosted on imgur.com, send takedown notices to them.
This is a 4chan archive - all of the content originated from them. If you need IP information for a Poster - you need to contact them. This website shows only archived content.