Mastering Deep Learning with LIMO-Robot Course - Python

Master deep learning with hands-on aproach using the LIMO robot.

Course Summary

This course offers a comprehensive introduction to deep learning with a focus on practical applications using the LIMO robot. You'll start by understanding the fundamental structure of deep learning models, exploring essential concepts such as neural networks, convolutional layers, and activation functions. The course will guide you through using pre-trained deep learning models, providing hands-on experience in implementing and adapting these models for various tasks. Additionally, you will learn how to train your own deep learning models, from data collection and preprocessing to model training and evaluation. By the end of the course, you will be equipped with the skills to deploy deep learning models on the LIMO robot for real-world obstacle avoidance and object detection

What you will learn

Basics of deep learning models and how they work.
How to use YOLO for object detection
How to train an AlexNet model for obstacle avoidance

Course Overview

Introduction

A short introduction about what is deep learning and what you are going to learn in this course

Deep Learning Basics

Learn to address a data problem using a NN. You will see and understand the basic mathematics behind NN and what structure a NN should follow. Moreover, you will experiment with examples of regression and classification from a robotics perspective, using data from a ROS simulator. You will perform these exercises in Python and the Keras library from TensorFlow.

How to Program an L-layer Neural Network in Python

Learn how to program a whole NN from scratch using Keras

Hyperparameter Tuning

Review the hyperparameters of the basic structure of a NN. Also, learn how to organize data to input a NN and use its output error to get information about its performance. Finally, learn some valuable techniques to increase the performance and prediction of your model and see what parameters you'll need to remember.

Convolutional Neural Networks

This chapter reviews a special example of networks, called convolutional neural networks, or CNN. Their popularity never stops growing, and you will present them as a powerful tool to solve computer vision problems. You will present the mathematics of these nets and how they make use of traditional computer vision techniques within their neurons and connections. As you did with basic NN, you will be looking at neurons, connections, weights, biases, hyperparameters, and design, training, and prediction phases.

Object and People Recognition with Convolutional Networks

In this unit, we'll delve into advanced perception techniques in robotics, focusing on AI methods such as YOLO. We'll learn about how YOLO can be used to perform high level tasks such as: Object Detection and People pose Estimation

Obstacle avoidance deep learning training

Learn how to generate the training material for building an obstacle-avoiding AlexNet-based AI model.

Teachers

Ricardo Tellez

Dreaming of a world where robots actually understand what they are doing. Developing the definitive tool that will make it happen.

Miguel Angel Rodriguez

Crashing engineering problems. Building solutions.