EIEIOTECHNOVATION
← Training programmes

EIEIO / ARTIFICIAL INTELLIGENCE

Deep Learning Fundamentals

Course outline

2 days
Discuss this programme →

Duration

Deep Learning Fundamentals

2 days

Prerequisites

R-programming/Python Basic

Synopsis

This course provides a comprehensive introduction to Deep Learning, covering essential concepts, techniques, and applications. Participants will learn the fundamentals of neural networks, convolutional neural networks (CNNs), and other key Deep Learning architectures. Practical examples and hands-on exercises will help participants develop the skills necessary to implement Deep Learning models using popular frameworks like TensorFlow. Additionally, the course will explore advanced topics such as autoencoders, generative adversarial networks (GANs), and their limitations. Participants will also gain insights into how Deep Learning is applied to reinforcement learning (RL) and natural language processing (NLP), with practical examples and case studies.

Learning Objectives

  • 1. Understand the fundamental concepts and applications of Deep Learning.
  • 2. Learn about weights, activation functions, and the perceptron model.
  • 3. Explore neural networks, loss functions, and backpropagation.
  • 4. Implement Deep Learning models using TensorFlow and Python.
  • 5. Gain proficiency in building and training convolutional neural networks (CNNs).
  • 6. Understand transfer learning and advanced CNN architectures like RCNN.
  • 7. Explore autoencoders and their applications in data compression and generation.
  • 8. Learn about generative adversarial networks (GANs) and their limitations.
  • 9. Understand the key elements of reinforcement learning (RL) and its application in robotics.
  • 10. Gain insights into the application of Deep Learning in natural language processing (NLP), including

language translation and text classification.

Module 1: Introduction to Deep Learning

What is Deep Learning and its applications

Understanding weights, activation functions, and the perceptron model

Course Outline :: Deep Learning Fundamentals::

Data preprocessing and image augmentation using OpenCV

Module 2: Neural Networks

Overview of neural networks and their applications

Loss functions, backpropagation, and optimization algorithms

Implementing a basic neural network with Python and TensorFlow

Practical example: MNIST classification with neural networks

Module 3: Convolutional Neural Networks (CNNs)

Introduction to CNNs and their applications in computer vision

Convolutional and pooling layers

Implementing CNN layers in Python with TensorFlow

Transfer learning and advanced CNN architectures like RCNN

Module 4: Autoencoders and Generative Adversarial Networks (GANs)

Understanding autoencoders and their applications

Introduction to generative adversarial networks (GANs)

Building a simple GAN with the MNIST dataset

Limitations of GANs and deep convolutional GANs (DCGANs)

Module 5: Reinforcement Learning (RL)

Key elements of reinforcement learning (RL)

Introduction to the OpenAI Gym toolkit

Application of Deep Learning in RL, including robotic manipulation

Practical examples and case studies of RL applications

Module 6: Deep Learning in Natural Language Processing (NLP)

Introduction to NLP and its applications

Automatic language translation using Deep Learning models

Automatic text classification with Deep Learning

Practical examples and case studies in NLP

Target Audience

Data Scientists

Machine Learning Engineers

Software Developers

AI Enthusiasts interested in Deep Learning

Professionals seeking to apply Deep Learning techniques in computer vision, robotics, and natural language processing

Programme scope, delivery arrangements and suitability are confirmed during enquiry.