Practical guide to DL

https://blog.paperspace.com/a-practical-guide-to-deep-learning-in-6-months/


Stage 1
Learn Python

http://bedford-computing.co.uk/learning/wp-content/uploads/2015/10/No.Starch.Python.Oct_.2015.ISBN_.1593276036.pdf
https://pep8.org/

Data wrangling

  • os (For file management)
  • json (Quite a lot of datasets are in the json format)
  • Argparse (For writing neat scripts)
  • Pandas (For working with csv and other tabular data)


Plotting

  • OpenCV
  • Matplotlib
  • Science Stack
  • NumPy
  • SciPy
ML
Koggle

Deep learning
https://adeshpande3.github.io/adeshpande3.github.io/The-9-Deep-Learning-Papers-You-Need-To-Know-About.html

PyTorch
TensorFlow
Keras

- Build applications and open source them. 


Stage 2

Math
https://www.probabilitycourse.com/
https://www.deeplearningbook.org/contents/prob.html
https://cims.nyu.edu/~cfgranda/pages/DSGA1002_fall15/material/optimization.pdf
https://www.coursera.org/learn/multivariate-calculus-machine-learning
https://www.deeplearningbook.org/contents/numerical.html
https://www.deeplearningbook.org/contents/ml.html
http://users.isr.ist.utl.pt/~wurmd/Livros/school/Bishop%20-%20Pattern%20Recognition%20And%20Machine%20Learning%20-%20Springer%20%202006.pdf
Read the rest of the Deep Learning book (Ch. 6 - Ch. 12 cover the relevant bits)
https://blog.usejournal.com/what-i-learned-from-interviewing-at-multiple-ai-companies-and-start-ups-a9620415e4cc
https://stanford.edu/~shervine/teaching/cs-230.html
https://distill.pub/

- Continue working on bigger and more ambitious projects in Deep Learning. Push your projects to GitHub and have an active GitHub profile.
- A good way to learn more about Deep Learning is to reimplement a paper. Reimplementing a popular paper (from a big lab like FAIR, DeepMind, Google AI etc) will give you very good experience.
- Read the rest of the Deep Learning book (Ch. 6 - Ch. 12 cover the relevant bits)
- https://cs231n.github.io/
- Interviews = Data Structures and Algorithms + Math + Machine Learning + Deep Learning. A rough break up would be - Math = 40%, Classical Machine Learning = 30%, Deep Learning = 30%.
- Do remote gigs (AngelList is an awesome resource) or deploy a Machine Learning model like this: https://platerecognizer.com/
- Jupyter Lab/notebook is very good for experimentation and debugging, but has its cons. Use a standard text editor/IDE (Sublime Text, atom, PyCharm) over Jupyter Notebook. It’s faster and helps in writing good, reproducible code.
- Computer Vision: CVPR, ICCV, ECCV, BMVC.
- Machine Learning and Reinforcement Learning (Theoretical): NeurIPS, ICML, ICLR
- NLP: ACL, EMNLP, NAACL

No comments:

Post a Comment