Скачать или смотреть Building PyTorch: Mastering Matrix Multiplication and Linear Layers in MicroTorch

In this video, we dive deep into implementing matrix multiplication (dot product) and linear layers from scratch. Learn the calculus behind forward and backward passes, handle multi-dimensional tensors, and build PyTorch-style APIs with real code examples. We’ll cover gradient computation, broadcasting, and operator overloading—key foundations for neural network training.

MicroTorch Series Playlist:
   • Backpropagation: Building a PyTorch-Like L...  

Check the Jupyter Notebook:
https://github.com/nickovchinnikov/da...

Check my step-by-step MicroTorch tutorial:
https://datasanta.net/2025/04/03/micr...

Implement Matrix Multiplication with Backpropagation
Design Linear Layers with Bias
Master Gradient Tracking for Neural Networks

Ideal for developers and AI enthusiasts looking to understand tensor operations and build scalable deep learning frameworks. Subscribe to follow the series as we add more operations, optimizers, and advanced features to MicroTorch!

Join me on:
Telegram: https://t.me/datasantaa
Twitter: https://x.com/datasantaa

Timestamps:
00:07 - Introduction
00:30 - Understanding Dot Product Calculus
03:19 - Implementing Matrix Multiplication
04:29 - Adding Backward Pass for Gradients
09:23 - Create dot method and overload @
14:14 - Building Linear Layers with Bias
16:27 - Summary & Next Steps

#PyTorch #DeepLearning #Tensor #MatrixMultiplication #Backpropagation #AI #Python #MachineLearning