Deep Dive Deep Learning
- Created By raju2006
- Last Updated December 20th, 2023
- Overview
- Prerequisite
- Audience
- Audience
- Curriculum
Description:
Starting from the basics, you'll understand how neural networks learn, delve into backpropagation, and explore the mathematical principles behind them. You'll even code a neural network from scratch before building one using TensorFlow. Next, we'll tackle Convolutional Neural Networks, vital for computer vision, applying this knowledge to an image recognition project. Then, we'll explore sequence models and Recurrent Neural Networks, leading to a hands-on project in natural language processing. Elevate your Deep Learning skills with us and unlock the potential of AI perception.
We will begin by understanding neural networks and how they learn. We’ll discuss back propagation and some of the math behind neural networks. We’ll then code a neural network from scratch, for a fuller understanding, before coding one in TensorFlow.With this foundation, we’ll then delve intoConvolutional Neural Networks which are used largely for computer vision. We’ll use this understanding to do an image recognition project.Next, we’llturn to understanding sequence models and Recurrent Neural Networks. This will lead us into doing a project on natural language processing.
Course Code/Duration:
BDT5A / 3 Days
Learning Objectives:
After this course, you will be able to:
- Install Anaconda on a personal computer.
- Install TensorFlow
- Have a clear understanding ofdeep learning and its role in AI
- Understand neural networks
- Code a neural network from scratch
- Understand the architectural differences between deep neural networks and deep learning
- Use TensorFlow and Kerasto apply deep learning
- UnderstandConvolutional Neural Networks
- Do image recognition tasks
- Understand Recurrent Neural Networks
- Do natural language processing
- Do sentiment analysis
- Understand use cases for Convolutional Neural Networks
- Understand use cases for Recurrent Neural Networks
- Basic Python Programming
- Developers,Business Analysts who want to start a career in or want to learn about the exciting domain of Data Science and Machine Learning, Non-technical professionals who want to start a career in Machine Learning.
- Developers,Business Analysts who want to start a career in or want to learn about the exciting domain of Data Science and Machine Learning, Non-technical professionals who want to start a career in Machine Learning.
Course Outline:
Day 1
- Course Introduction
- Overview of Deep Learning
- Install Anaconda
- Milestone 1: Learn how to use Jupyter Notebooks
- Essential libraries
- TensorFlow
- Keras
- NumPy
- Scikit Learn
- Introduction to neural networks
- The math behind neural networks
- Back propagation
- Understanding the intuition behind neural networks
- Milestone 2: Coding a neural network from scratch
- Deep neural networks
- Understanding TensorFlow
- Milestone 3: Applying neural networks using TensorFlow/Keras
Day 2
- From Deep Neural Networks to Deep Learning
- Understanding unstructured data
- Image recognition
- Introduction to Convolutional Neural Networks (CNN)
- Convolutional layers
- Pooling layers
- Fully-connected layers
- Milestone 4: Using TensorFlow to create a CNN
- Milestone 5: Image recognition project
Day 3
- Understanding sequence models
- Introduction to Recurrent Neural Networks (RNN)
- Natural Language Processing (NLP)
- Text preprocessing
- Word embeddings
- Sentiment analysis
- Milestone 6:Using TensorFlow to create an RNN
- Milestone 7: Natural Language Processing project
- Introduction to Auto Encoders
- Introduction to Generative Adversarial Networks (GAN)
Structured Activity/Exercises/Case Studies:
Day 1
- Milestone 1 – Learn how to use Jupyter Notebooks
- Milestone 2 – Coding a neural network from scratch
- Milestone 3 – Applying neural networks using TensorFlow/Keras
Day 2
- Milestone4 – Using TensorFlow to create a CNN
- Milestone 5 –Image recognition project
Day 3
- Milestone 6 – Using TensorFlow to create an RNN
- Milestone 7 – Natural Language Processing project
Training material provided:
Yes (Digital format)
