Packt Publishing – Mathematics Behind Backpropagation – Theory and Python Code 2026
English | Tutorial | Size: 981.92 MB
In this 4-hour course, you will gain a deep understanding of the mathematics behind backpropagation and its implementation in Python. The course will cover everything from the basics of derivatives and gradients to building and training your own neural network from scratch.
What I will be able to do after this course
Master the mathematics of backpropagation for neural networks
Understand derivatives, partial derivatives, and gradients
Implement backpropagation from scratch using Python code
Dive deep into gradient descent and learning rates
Explore the significance of computational graphs in AI
Course Instructor(s)
Patrik Szepesi is a senior Machine Learning Engineer with experience in autonomous vehicles, banking, and healthcare. He has contributed to groundbreaking projects at Morgan Stanley and John Deere, and published research in top journals. Patrik currently works in healthcare AI development and holds advanced AWS certifications.
DOWNLOAD: