Check out my resume here.

Roadmap to ML and DL

This is my learning path to Machine Learning and Deep Learning

"”The brain sure as hell doesn’t work by somebody programming in rules. -Geoffrey Hinton””

The way i just follow is top down method and its hardway to understand but its more efficient that any other . First we should know the basics whats is ML and whats is DL and its classification I just came through internet and get this image to classify both ML and Dl in

Artificial Intelligence

Difference in AI and ML subset of AIHere we can see that Artificial intelligence is a combination of Ml and Dl And NN

In previous days Arthur Lee Samuel who invented the term Machine Learning and the Checkers -program was the first successful machine learning program Later many came and get eager in this field the hype word ML came into the world .

So for learning Ml i am suggesting some self paced ML resources which is world class

For learning there is a path i just follow the top down here first i am mentioning from NN →DL →Ml →Maths →Python..sorry to say this may be very awkward but beleive me it works

For Machine learning

  1. Andrew Ng Machine Learning
  2. Fast.ai
  3. Google Machine Learning crash course
  4. Machine Learning tutorial form kaggle

Deep learning resources

  1. MIT Introduction to deep learning
  2. fast.ai
  3. Deep learning- Coursera(Andrew Ng)

BLOG

Rather than going for tutorials i mostly used to read blog, because bloggers mostly express their outcomes by writing so yes that’s why i am here to express my outcome here

The highly curated blog like

  1. colah blog
  2. karpathy blog
  3. distill

And one blog which i loved most otoro hadmaru blog

GITHUB repos

The best Github resources that gives you free code tutorials as well as an idea that how to code.

  1. A top-down, practical guide to learn AI, Deep learning and Machine Learning here

  2. A curated list of awesome Machine Learning frameworks, libraries and software. here

  3. PyTorch Tutorial for Deep Learning Researchers.here

  4. Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data spark here

  5. A list of popular github projects related to deep learning here

  6. Deep Learning and deep reinforcement learning research papers and some codes here

  7. Top 200 deep learning Github repositories sorted by the number of stars here

  8. A curated list of awesome Deep Learning tutorials, projects and communities. …github.com

And also check out my github repo [here](https://github.com/geekylax)__

Here i mentioned some awesome repos for Machine Learning as well as Deep Learning also some beautifully documented NLP resources

check out forked repos here which are most important and starred repo here which are in construction

I am doing some projects tutorials form what i learn from the resources mentioned above here

Contribute to geekylax/Projects_from_Tutorials

Please fork my repo and add , get pull request to make changes

WEBSITES

Websites which are useful to learn

  1. Analytics vidhya
  2. kdnuggets
  3. superdatascience
  4. datasciencecentral
  5. hackernoon

YOUTUBE Resources

The best youtube video tutorials that i inspired a lot

  1. sirajraval

  2. move37

sorry to say this the one and only siraj is best for youtube resources you can get most of learnings here

MATH resources

Basic Maths tutorials resources are useful to get an idea sorry to say this i get to do this at last after doing these above steps

  1. khanacademy
  2. 3blue1brown
  3. fastai numeric algebra

So yes tatsol after finishing these tutorials i am doing research in quantum computing for Deeplearning So i will post my knowledge in my upcoming post

def print_hi(name)
  puts "Hi, #{name}"
end
print_hi('Tom')
#=> prints 'Hi, Tom' to STDOUT.

Check out the Jekyll docs for more info on how to get the most out of Jekyll. File all bugs/feature requests at Jekyll’s GitHub repo. If you have questions, you can ask them on Jekyll Talk.