Introduction to Deep Learning

Author:

Dennis Núñez Fernández
https://dennishnf.com

Description:

This repository provides basic concepts for Deep Learning and practical examples for a better understanding of the topics, all examples are provided and are intended to be executed in Google Colab and using your own dataset. The code was implemented in Python 3.6 and using Keras 2.x and Tensorflow 2.x frameworks.

Note 1: After opening the main.ipynb files in GitHub you can visualize the code previously executed, or you can click on "Open in Colab" and see the folder in my Google Drive. Then DOWNLOAD the folder and then UPLOAD the folder to your Google Drive, and modify some paths in the main.ipynb file of some labs according to your path in order to work properly. I strongly recommend downloading and uploading the lab folders to avoid different problems about shared files on Google Drive.

Note 2: For datasets, zip files and temporal location in the tmp folder at Google Colab space were used because extracting data from this is faster compared to extracting data from your Google drive.

Table of contents:

Lect 0: Introduction to AI and Deep Learning

Lect 1: Tools: Google Colab, Tensorflow, Keras
Lab 1: Use of tools and basic examples

Lect 2: Basic concepts of neural networks
Lab 2: Classification using Multilayer Perceptron

Lect 3: Basic classification concepts
Lab 3: Classification using CNNs

Lect 4: Basic concepts of object detection
Lab 4: Object detection using Faster R-CNN

Lect 5: Basic concepts of segmentation
Lab 5: Segmentation using the U-Net

Lect 6: Additional contents about AI and DL

Resources:

You can find a list of additional resources like free course, papers, books and more in this link.