Deep Learning: Convolutional Neural Networks for developers

Name: Deep Learning: Convolutional Neural Networks for developers
Rating: 4.4 (44 reviews)

This course will teach you Deep learning focusing on Convolution Neural Networks architectures

Created byAlexsandro Souza

Last updated 6/2024

English

What you'll learn

Convolutional neural network architectures
Computer vision algorithims
How to implement a Deep Neural Network from scratch
How back-propagation algorithm works
How to search similar images
How to build multi task models

Course content

1 section • 12 lectures • 2h 49m total length

Introduction4:51
Source code
You can find all the source code on Github
Working with images and Numpy6:09
In this lab, we are going to learn how images are represented in a 3-dimensional array and how we can easily manipulate it with NumPy
Image convolution with Numpy6:55
In this lab, we'll explore what is convolutions and how they work. Together with convolutions, you'll use something called 'Pooling', which compresses your image, further emphasising the features. You'll also see how pooling works in this lab.
Building a neural network from scratch - part 111:51
In this section, we will learn how to implement the backpropagation algorithm from scratch using Python.
Building a neural network from scratch - part 218:09
In this section, we will learn how to implement the backpropagation algorithm from scratch using Python.
Building a neural network with PyTorch8:53
In the previous session, we built our Model architecture from scratch without any deep learning framework. In this session, we will build the same model but this time using the Pytorch framework
Convolution Neural Network with PyTorch26:50
In this session, we will learn how to build a Convolutional neural network with Pytorch.
CNN and Autoencoder - image interpolation19:01
In this section, We are going to learn how to work with autoencoders to generate Latent Space/ feature map and from there do some nice things with images
Image similarity - Image reverse search engine9:39
In this section, we will learn how to implement the backpropagation algorithm from scratch using Python.
Developing a multitasking model34:34
Playing with Generative Adversarial Networks (GAN)22:14

Requirements

No Deep Learning experience needed. You will learn everything you need to know

Description

This course will teach you Deep learning focusing on Convolution Neural Net architectures. It is structured to help you genuinely learn Deep Learning by starting from the basics until advanced concepts. We will begin learning what it is under the hood of Deep learning frameworks like Tensorflow and Pytorch, then move to advanced Deep learning Architecture with Pytorch.

During our journey, we will also have projects exploring some critical concepts of Deep learning and computer vision, such as: what is an image; what are convolutions; how to implement a vanilla neural network; how back-propagation works; how to use transfer learning and more.

All examples are written in Python and Jupyter notebooks with tons of comments to help you to follow the implementation. Even if you don’t know Python well, you will be able to follow the code and learn from the examples.

The advanced part of this project will require GPU but don’t worry because those examples are ready to run on Google Colab with just one click, no setup required, and it is free! You will only need to have a Google account.

By following this course until the end, you will get insights, and you will feel empowered to leverage all recent innovations in the Deep Learning field to improve the experience of your projects.

Who this course is for:

Developers curious about deep learning and AI