Sandeep Pandey

Sandeep Pandey

Engineer with a PhD in applied machine learning and scientific computing.

Resources: Data Science, Machine Learning, Python

2 minute read

Published:

This is a (growing) general-purpose list (for my own documentation purpose) of some of the resources which I have found very helpful.

Machine Learning (ML) and Data Science (DS)

Practial courses for ML:

In my opinion, before jumping to the ML or DS theory part (or even finalizing the journey), one should learn about why ML/DS is critical and how it looks. In the end, it’s just the cocktail of programming, applied mathematics, and domain knowledge. Following is the recommended list to begin with:

  • An excellent overview of deep learning from Lex Fridman on YouTube.
  • TensorFlow 2.0 Beginner Tutorials : Well described tutorials focusing upon TensorFlow with detailed concept from the application perspective.
  • Udemy is a go-to place to learn the application part. Courses can be bought often for a cheaper price and the good part is that they are structured and everything is in one place. I really enjoyed this course as a first step. This course can be bought for < 19 Euro (If it’s not in this price range then wait for some time, they often have a special offer like every other week).

Theoretical resources:

Python

Learning Python (basic and advance)

Swift

Applied Statistics

Markov Chain

Hidden Markov Model

Lyapunov Exponent

You May Also Enjoy

Machine Learning Applied to Stock Market Prediction: A Comparison between LSTM and ESN

5 minute read

Published:

My use-case is focused on stock market price prediction, especially the opening price for a given stock. I haven’t focused too much on the hyperparameter tuning, rather aimed towards building the basic model and comparing some results. Unlike the scientific work, where my network has to predict autonomously provided an initial data, here we have the luxury to get input continuously i.e. by the end of the day we will have all the inputs so that we can guess what will be the opening price tomorrow.