machine-learning-for-software-engineers
machine-learning-for-software-engineers copied to clipboard
ZuzooVn
Need advice about Deep Learning roadmap.
I think the best way to get started with deep learning is determine the field that you are most interested in, such as Natural Language Processing, Computer Vision and Speech Recognition. Whenever that is determined, you try to find books, online courses or any other resources that applies deep learning for the determined field.
For me, I am interested in NLP, so, I decided to get started in deep learning by taking "Deep Learning for Natural Language Processing". http://cs224d.stanford.edu/syllabus.html
If you haven't decided yet the field, then you can get started with the general idea of Deep Learning. You can begin with this course https://www.coursera.org/learn/neural-networks and this book http://www.deeplearningbook.org/
After learning the concepts, you may need to know the libraries and programming languages that help you to implement a deep learning based project. Tensorflow, theano and keras in Python are great tools for that. This course will help you in Tensorflow https://www.udacity.com/course/deep-learning--ud730
There are some interesting blogs that write about Deep Learning, such as http://colah.github.io/ http://www.wildml.com/ http://karpathy.github.io/
Finally, to practice more on using deep learning, you can apply its techniques in Kaggle https://www.kaggle.com/
Kaggle is a great place for practicing in Machine Learning.
Thank you so much!
On Mon, Oct 17, 2016 at 5:24 AM, Ahmed Hani Ibrahim < [email protected]> wrote:
I think the best way to get started with deep learning is determine the field that you are most interested in, such as Natural Language Processing, Computer Vision and Speech Recognition. Whenever that is determined, you try to find books, online courses or any other resources that applies deep learning for the determined field.
For me, I am interested in NLP, so, I decided to get started in deep learning by taking "Deep Learning for Natural Language Processing". http://cs224d.stanford.edu/syllabus.html
If you haven't decided yet the field, then you can get started with the general idea of Deep Learning. You can begin with this course https://www.coursera.org/learn/neural-networks and this book http://www.deeplearningbook.org/
After learning the concepts, you may need to know the libraries and programming languages that help you to implement a deep learning based project. Tensorflow, theano and keras in Python are great tools for that. This course will help you in Tensorflow https://www.udacity.com/ course/deep-learning--ud730
Finally, to practice more on using deep learning, you can apply its techniques in Kaggle https://www.kaggle.com/
Kaggle is a great place for practicing in Machine Learning.
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/ZuzooVn/machine-learning-for-software-engineers/issues/3#issuecomment-254079566, or mute the thread https://github.com/notifications/unsubscribe-auth/ANio0CepuSI3-C8tcqaNzm5ujttjX2BOks5q0qQagaJpZM4KX8ON .
Tensorflow is a popular library so far for deep learning. I found this repo https://github.com/alrojo/tensorflow-tutorial very useful. For each notebook, there are resources for deep learning concepts, algorithms, then you practice and finally apply on a kaggle challenge.
What do you think about this road map? http://blog.digitalmind.io/post/deep-learning. It's not the top-down method, but it has a lot of good resources.
Here is another hot theoretical approach: https://github.com/songrotek/Deep-Learning-Papers-Reading-Roadmap. But it is not suitable for everyone
I received comments from Hacker News's user annnnd for this roadmap.
For someone who has basic background knowledge in ML and wants to know more about NN and DL, my list would be:
- Neural Networks and Deep Learning (http://neuralnetworksanddeeplearning.com/) - perfect overview, go over it twice at least (the second time you will understand much of the decisions in the start)
- Tensorflow and deep learning, without a PhD (https://www.youtube.com/watch?v=sEciSlAClL8) - as much as I hate video lectures, this one was worth it; a good complement to the book above
- Theano Tutorial (http://deeplearning.net/software/theano/tutorial/index.html) - using Theano or TensorFlow takes some getting used to. I found TensorFlow documentation absolutely horrible for beginners, probably because the authors expect users to already know such frameworks. Once you learn Theano you won't have trouble with TensorFlow (if that's what you want to use). Then there are more specific papers, but I guess those depend on the problem at hand.
Open Source Deep Learning Curriculum: http://www.deeplearningweekly.com/pages/open_source_deep_learning_curriculum
Deep Learning is a vast filed but this can be covered very easily if we have a good instructor in the house , so i would suggest to go for Coursera Deep Learning Specialization its the best ,just keep the trust in it and u will be the best in your field
LInk - https://www.coursera.org/specializations/deep-learning
