Search found 39 matches

by lazyprogrammer
Wed Sep 16, 2020 4:55 pm
Forum: Deep Learning Prerequisites: The Numpy Stack in Python
Topic: Matplotlib exercise
Replies: 9
Views: 1049

Re: Matplotlib exercise

Did you mean to say that "it says 0,0,0" but it should be "1,1,0"?
by lazyprogrammer
Fri Aug 07, 2020 6:04 pm
Forum: General Discussion
Topic: Deep Dream code not working
Replies: 4
Views: 291

Re: Deep Dream code not working

Could you let me know which email you use on deeplearningcourses.com?
by lazyprogrammer
Thu Jul 30, 2020 5:09 am
Forum: General Discussion
Topic: Any course on Transformer/BERT?
Replies: 1
Views: 235

Re: Any course on Transformer/BERT?

It's going to be in a separate course.
by lazyprogrammer
Wed Jul 29, 2020 6:00 am
Forum: General Discussion
Topic: Absolute Error or Maximum Deviation using linear programming
Replies: 4
Views: 374

Re: Absolute Error or Maximum Deviation using linear programming

I would be tempted to also try out cvxopt. I think Stephen Boyd said it can handle thousands x thousands just fine. Also interestingly, it says this on Wikipedia: "In the case p = 1, this corresponds to least absolute deviation regression (in this case, the problem would be better approached by use ...
by lazyprogrammer
Tue Jul 28, 2020 5:41 am
Forum: Natural Language Processing with Deep Learning in Python
Topic: There might be a mistake in your code
Replies: 1
Views: 353

Re: There might be a mistake in your code

Oh, you might want to have a look on Github, that was updated a few years ago (also have a look at the preceding theory lecture, everything is derived there).
by lazyprogrammer
Tue Jul 28, 2020 5:36 am
Forum: General Discussion
Topic: Absolute Error or Maximum Deviation using linear programming
Replies: 4
Views: 374

Re: Absolute Error or Maximum Deviation using linear programming

Practical is in the eye of the beholder. Sometimes people watch the videos and think all computation should be complete within seconds. In my early deep learning courses, students were surprised when training took hours. Researchers will wait days or weeks. Sometimes, the obvious solution evades us....
by lazyprogrammer
Wed Jul 01, 2020 2:10 pm
Forum: General Discussion
Topic: What course should I take for making a coughing recognition app?
Replies: 3
Views: 423

Re: What course should I take for making a coughing recognition app?

I cover this in my course "Advanced NLP and RNNs" (only in the VIP version located at https://deeplearningcourses.com/c/deep-learning-advanced-nlp). However, I'd urge you to double check the prerequisites for the course, as well as read the article: https://lazyprogrammer.me/path-to-mastering-natura...
by lazyprogrammer
Tue Jun 30, 2020 5:45 pm
Forum: General Discussion
Topic: What course should I take for making a coughing recognition app?
Replies: 3
Views: 423

Re: What course should I take for making a coughing recognition app?

Thanks for your inquiry. There's not enough information in your post. You can use any kind of machine learning model, therefore, learn "machine learning", which is all of the courses. I would recommend watching the lecture "What order should I take your courses in?" which can be found here: https://...
by lazyprogrammer
Sat Jun 20, 2020 11:45 pm
Forum: Natural Language Processing with Deep Learning in Python
Topic: A question on the global average in Matrix Factorization
Replies: 4
Views: 545

Re: A question on the global average in Matrix Factorization

Thanks for your inquiry.

You'd have to experiment to determine what the best configuration is.

Anecdotally I have found that more data usually leads to better results.
by lazyprogrammer
Fri Jun 19, 2020 8:36 pm
Forum: Natural Language Processing with Deep Learning in Python
Topic: A question on the global average in Matrix Factorization
Replies: 4
Views: 545

Re: A question on the global average in Matrix Factorization

Generally speaking machine learning models fit more easily to functions centered around 0. However, you should follow my rule "machine learning is experimentation, not philosophy". Trying to use philosophy is very confusing (as you are seeing). Instead of trying to guess how a computer program behav...

Go to advanced search