I just started playing around with machine learning in Python today. It's so fucking amazing, man!
All the concepts that come up when you search for tutorials on YouTube (you know, neural networks, SVM, Linear/Logic regression and all that fun stuff) seem overwhelming at first. I must admit, it took me more than 5 hours just to get everything set up the way it should be but, the end result was so satisfying when it finally worked (after ~100 errors).
If any of you guys want to start, I suggest visiting these YouTube channels:
- https://youtube.com/channel/...
- http://youtube.com/playlist/...

  • 5
    Thanks mate.
  • 20
    please try to understand the math behind it aswell. otherwise it will just stay a black box between input and output
  • 9
    Can e
    Recommended a online course (for free, you only need to pay if you want a paper "xy was here")
    It's coursera.org/learn/machine-learning (taught by Stanford Prof)
    The only 'downside' is, that it is made up as a lecture, so each week there's new stuff.
    I think it's worth to take a look at.
  • 1
    @luckbot it's not as difficult as people perceive it to be. Once you get the main concepts down (along with the math), you're pretty much good to go.
  • 1
    @hacker yeah, i know. had machine learning and pattern recognition last semester. but its still usefull to know what hidden layers are doing, how svm work and so on.
    deep learning is another step though.
  • 2
    Well, the really hard work is prepare the data. Someone called it “data massaging“, i like this term because you gotta have to put a lot of passion in it ;)
  • 0
    If anyone has a really good pointer on backpropogation i am all ears. I can't figure out the wikipedia notation like math dumps on it.
  • 1
  • 0
    @hacker yeah, sorry. Once he starts ratling about formulas without explaining every variable i am lost. He uses words i know, in a way i don't understand.
Add Comment