Description
Python: Write Your Own Deep Learning Framework From Scratch is a course on building your own deep learning framework using pure Python published by Udemy Online Academy. This is an in-depth and practical course that teaches you how neural networks work by guiding you step-by-step through building your own deep learning framework using pure Python – without relying on high-level libraries. You’ll explore the basics of tensors, automatic differentiation, computational graphs, forward and back propagation, optimization algorithms like gradient descent, and how layers and activations work in real-world models. Throughout the course, you’ll apply these concepts by writing core components like tensor operations, loss functions, optimizers, and model trainers from scratch, and you’ll gain a thorough understanding of what’s going on in popular frameworks like TensorFlow and PyTorch.
This course teaches you how to build a simple, PyTorch-like deep learning framework from scratch. This course covers the core mechanics of automatic differentiation and neural network abstractions. In this course, I will walk you through the process of building a modular workflow using Python and NumPy. You will see how to implement the im2col algorithm for efficient convolution and handle sequential data for time series tasks. Finally, we will write fully functional CNN and RNN architectures from the ground up, ensuring a deep understanding of these powerful models.
What you will learn in Python: Write Your Own Deep Learning Framework From Scratch:
- How to write a deep learning framework using pure Python and NumPy code.
- How to build a functional Autograd engine from scratch.
- Be able to implement core classes such as variable, function, and module.
- Be able to build a tensor engine that supports spread and matrix operations.
- How to implement activation functions such as ReLU, Sigmoid, and Softmax.
- How to build a data pipeline including a dataset and DataLoader for mini-batch training.
- Be able to implement optimizers such as Stochastic Gradient Descent (SGD).
- How to train and evaluate models on the MNIST dataset.
- How to implement Convolutional Neural Networks (CNN) from the ground up.
- Be able to understand the im2col algorithm for convolutions.
- How to implement Recurrent Neural Networks (RNN) from the ground up.
- And…
Course specifications
Publisher: Udemy
Instructors: x-BIT Development
Language: English
Level: Introductory to Advanced
Number of Lessons: 90
Duration: 7 hours and 29 minutes
Course topics
Python: Write Your Own Deep Learning Framework From Scratch Prerequisites
Basic Python programming skills (familiarity with classes, functions, and NumPy basics).
Basic Calculus and Linear Algebra, specifically derivatives and the Chain Rule, matrix multiplication. If you’re not a fan of math, you can simply follow the code to see how it works in action
Basic Deep Learning concepts: Knowing the basics of how models train and common architectures like CNNs and RNNs. We’ll cover the basics, and more importantly, we’ll take it a step further through learning by doing.
A curiosity to see how a deep learning framework is built and a willingness to follow along with the code.
No prior experience in deep learning framework development is required—we will build everything step by step.
Pictures
Python: Write Your Own Deep Learning Framework From Scratch introduction video
Installation guide
After Extract, watch with your favorite Player.
English subtitle
Quality: 1080p
Downloadly link
Rapidgator link
File password (s): www.downloadly.ir
Size
3.2 GB
