If you want more than a 4 lecture course, I recommend Nando de Freitas's course. It's very high quality and free.
https://www.cs.ox.ac.uk/people/nando.defreitas/machinelearni...
Google's Free Deep Learning Course
41–50 of 66 posts
Re: Google's Free Deep Learning Course
#42I'm going through the course right now, and the instructor is saying some strange things, clearly (to me) ignoring that what he's saying is only true in very specific contexts. For example, in the video I just watched he said "the natural way to compute the distance between two vectors is using cross entropy." And then he goes on to describe some unnatural features of cross entropy. The truly "natural" way to compute…
Because he wrote one of the most successful ones?
Re: Google's Free Deep Learning Course
#43Would it be beneficial for me as a developer to take these machine learning courses? I took a course in the uni a while back and know the general techniques, but I'm not sure how it would help me in my career unless I'm doing some cutting edge work in the field or focusing on a machine learning career, in which case wouldn't I need to be pursuing a postdoc or something in it?
If you can make the time than learning new things and taking courses is always a good idea. You never know where you're going to end up as a developer. Who knows you may end up changing the course of your career. Also machine learning and AI are all becoming big fields.
TBH, I like machine learning in terms of its applications, but I have no desire to go into the field in order to do research, or deal with statistics, etc. I would rather just use it as part of my software that I am building. To that extent, how helpful is it for me to take these deep learning type courses?
Re: Google's Free Deep Learning Course
#44I'm going through the course right now, and the instructor is saying some strange things, clearly (to me) ignoring that what he's saying is only true in very specific contexts. For example, in the video I just watched he said "the natural way to compute the distance between two vectors is using cross entropy." And then he goes on to describe some unnatural features of cross entropy. The truly "natural" way to compute…
Because he wrote one of the most successful ones?
My goal is to understand it for my own purposes, not to put on blinders and replicate his work.
Re: Google's Free Deep Learning Course
#45If you want more than a 4 lecture course, I recommend Nando de Freitas's course. It's very high quality and free. https://www.cs.ox.ac.uk/people/nando.defreitas/machinelearni...
To be clear, the posted course is not a survey course in machine learning. It is instead a more practical course on using TensorFlow to build deep neural network architectures useful for certain tasks.
The link the OP posted is a (great) survey course dedicated to machine learning as a whole, which includes methods other than deep learning.
Re: Google's Free Deep Learning Course
#46Will the projects/assignments be workable on Windows, or would I need Linux et al for these?
And if not natively (using docker/VMs), would they be able to use NVidia CUDA card on my system? And how much disk space would be needed.
Thanks.
Re: Google's Free Deep Learning Course
#47I'm going through the course right now, and the instructor is saying some strange things, clearly (to me) ignoring that what he's saying is only true in very specific contexts. For example, in the video I just watched he said "the natural way to compute the distance between two vectors is using cross entropy." And then he goes on to describe some unnatural features of cross entropy. The truly "natural" way to compute…
Because he wrote one of the most successful ones?
"Just trust me, I'm smarter than you are." isn't the best stance for a teacher to take.
Re: Google's Free Deep Learning Course
#48I'm going through the course right now, and the instructor is saying some strange things, clearly (to me) ignoring that what he's saying is only true in very specific contexts. For example, in the video I just watched he said "the natural way to compute the distance between two vectors is using cross entropy." And then he goes on to describe some unnatural features of cross entropy. The truly "natural" way to compute…
It's a course assuming some background in ML.
For _probability_ vectors, there is a distance measure called cross-entropy. It's a standard error measure in classification problems. It has some important properties different from the Euclidean distance (especially for low probabilities) and there is information-theoretic interpretation.
More on it:
- http://stats.stackexchange.com/questions/80967/qualitively-w...
Re: Google's Free Deep Learning Course
#49For people interested, Stanford has an excellent online course on deep-learning with an emphasis on convolutional networks. [1]
It comes with video, notes, all the math, cool ipython notebooks and will let you implement a deepish network from scratch. That includes doing backprop through the svn, softmax, max-pool, conv and ReLU layers.
After that you should be more than capable to build a 'real' net using your favourite lib (Tensorflow, theano etc).
Re: Google's Free Deep Learning Course
#50I'm going through the course right now, and the instructor is saying some strange things, clearly (to me) ignoring that what he's saying is only true in very specific contexts. For example, in the video I just watched he said "the natural way to compute the distance between two vectors is using cross entropy." And then he goes on to describe some unnatural features of cross entropy. The truly "natural" way to compute…
I think you forget to read:
================================
Prerequisites and Requirements
This is an intermediate to advanced level course. Prior to taking this course, and in addition to the prerequisites and requirements outlined for the Machine Learning Engineer Nanodegree program, you should possess the following experience and skills:
Minimum 2 years of programming experience (preferably in Python) Git and GitHub experience (assignment code is in a GitHub repo) Basic machine learning knowledge (especially supervised learning) Basic statistics knowledge (mean, variance, standard deviation, etc.) Linear algebra (vectors, matrices, etc.) Calculus (differentiation, integration, partial derivatives, etc.) See the Technology Requirements for using Udacity.