Learn Machine Learning, Deep Learning, and Artificial Intelligence
We started to implement algorithms using an end-to-end machine learning framework: PyTorch 
We followed the free course named ‘Secure and Private AI’ given by Udacity 
And, we started writing a new section of our about-to-be “software engineering” book : Secure and Private Artificial Intelligence 
Come back to reality, study your mathematical courses
It is time to remember your first-grade courses in mathematics and statistics:
- vectors, matrix (1-dimension, 2-D, and 3D), matrix multiplication
- random normal variables, loss function (cost)
and then you can start applying the theory :
- Build neural networks
- Train the neural network in four steps:
- Forward Propagation
- Loss computation
- Updating the parameters
- Finally, when these steps are executed for a number of epochs with a large number of training examples, the loss is reduced to a minimum value 
- The final weight and bias values are obtained which can then be used to make predictions on the unseen data. 
Roll your sleeves up and code!
After a few lines of code, the download of samples you find out that a model without training is useless.
The figure indicates that they are as many chances that the figure on the left (number 6) is a 0, 1, 2… or 9!
Several hours later, a few lines of code and training of the model using already-trained data and the prediction on unseen data indicates with a very high level of confidence which number is drawn.
 PyTorch : https://pytorch.org
 Udacity: Secure and Private AI: https://classroom.udacity.com/courses/ud185
 Software engineering at ALT-F1: https://alt-f1-software-architecture.readthedocs.io
 HR curriculum: Secure and Private Artificial Intelligence: https://alt-f1-software-architecture.readthedocs.io/en/latest/02-03.HR_management.html#secure-and-private-artificial-intelligence
 Get Started with PyTorch – Learn How to Build Quick & Accurate Neural Networks (with 4 Case Studies!) : https://www.analyticsvidhya.com/blog/2019/01/guide-pytorch-neural-networks-case-studies