Getting Started with Deep Learning and Python
Because of the current accomplishments of artificial neural networks across a wide range of tasks deep learning has turned out to be to a great degree prevalent. This post plans to be a beginning stage for those inspired by adopting more about it.
To Choose which language Python Vs R is good for Machine Learning to see the case study here.
In the event that you as of now have an essential comprehension of :
a.) linear algebra,
c.) probability and
d.) any programming experience
I suggest beginning with below Online Courses and Books.
Once you got these basics you can start these 6 Easy steps to start learning Basics of Deep Learning:
Step 1. Recommended Books on Deep Learning
Step 2. Take Online Free Courses on Deep Learning
I would recommend seeing the 7 Best Online courses to Learn Deep Learning
Step 3. Must See Videos and Lectures on Deep Learning
Firstly I would recommend first below videos:
3.)Deep Learning, Self-Taught Learning, and Unsupervised Feature Learning By Andrew Ng
4.) Deep Learning of Representations by Yoshua bengio
5.) Machine Learning Discussion Group – Deep Learning w/ Stanford AI Labby Adam Coates
6.) Making Sense of the World with Deep Learning By Adam Coates
7.) The Unreasonable Effectiveness of Deep Learning by Yann LeCun
8.) Visual Perception with Deep Learning By Yann LeCun
9.) The Next Generation of Neural Networks By Geoffrey Hinton at GoogleTechTalks
10.) Demystifying Unsupervised Feature Learning By Adam Coates
11.) Unsupervised Deep Learning – Stanford by Andrew Ng in Stanford (2011)
13.) Recent Developments in Deep Learning By Geoff Hinton
Step 4. Deep Learning FREE Tutorials
Firstly I would recommend first below 2 links:
1.) The Best Machine Learning Tutorials On The Web
2.) Deep Learning for NLP (without Magic)
3.) Deep Learning from the Bottom-up
4.) A Deep Learning Tutorial: From Perceptrons to Deep Networks
5.) Theano Tutorial
6.) UFLDL Tutorial 1
7.) UFLDL Tutorial 2
9.) VGG Convolutional Neural Networks Practical
10.) Neural Networks for Matlab
12.) UC Irvine Machine Learning Repository
13.) Berkeley Segmentation Dataset 500
Step 5. Frameworks on Deep Learning
7. Neon – Python based Deep Learning Framework
12. Chainer – A flexible framework of neural networks for deep learning
14. Nvidia DIGITS – a web app based on Caffe
15. Minerva – a fast and flexible tool for deep learning on multi-GPU
16. Keras – Theano based Deep Learning Library
17. RNNLM Toolkit
18. MatConvNet: CNNs for MATLAB
Step 6. Go through White Papers on Deep Learning
course site (10-805 DEEP LEARNING) for a perusing bunch @ CMU on Deep Learning. The prior papers traverse the unassuming beginnings of the neural system to the begin of the deep learning worldview. This course is as yet in progress and in this way more papers are en route:
The accompanying connection has an extremely far-reaching perusing list for deep learning papers. Somebody comfortable with machine learning basics will increase much from a chose to peruse of the below page link:
Along these lines, you would build up a significantly more extensive comprehension of the subject.
Miscellaneous on Deep Learning
1. Here’s a list of resources for people starting out with deep learning
2. Caffe Webinar
3. Misc from MIT’s ‘Advanced Natural Language Processing’ course
4. Google Plus – Deep Learning Community
5. TorontoDeepLEarning convnet
6. 100 Best Github Resources in Github for DL
8. Caffe DockerFile
9. Implementing a Distributed Deep Learning Network over Spark
10. Torch7 Cheat sheet
11. Google deepdream – Neural Network art
12. Misc from MIT’s ‘Machine Learning’ course
13. A chess AI that learns to play chess using deep learning.
14. Reproducing the results of “Playing Atari with Deep Reinforcement Learning” by DeepMind
15. The original code from the DeepMind article + tweaks
16. Misc from MIT’s ‘Neural Coding and Perception of Sound‘ course
17. A recurrent neural network designed to generate classical music.
18. Misc from MIT’s ‘Networks for Learning: Regression and Classification’ course
The most comprehensive source of information on Deep Learning I’ve found is Stanford CS231 class.
Just watch all these lectures and do all assignments.
Note: Want to know in-depth AI and ML latest resources around the web you MUST see this index page here.
PS: Also you might want to see Top 50 Awesome Deep Learning Projects on GitHub
In the event that you’d get a kick out of the chance to prepare neural systems, you ought to presumably do it on a GPU. You don’t need to, however, it’s significantly quicker on the off chance that you do. NVIDIA cards are the business standard, and keeping in mind that most research labs utilize designs cards, there are a couple of reasonable cards that can likewise complete the work.
Don’t be afraid to fail. The majority of your time in deep learning will be spent trying to figure out why an algorithm didn’t pan out how you expected or why I got the error ABC… that’s normal. Tenacity is key. Just go for it. If you think some algorithm might work… try it with a small set of data and see how it does. These early projects are a sandbox for learning the methods by failing – to make use of it and give everything a try that makes sense.