Course Highlights
Ever dreamt of navigating the intricate pathways of the human brain’s counterparts in the machine world? Welcome to the “Deep Learning & Neural Networks Python – Keras” course, an odyssey that paints a vivid picture of the intertwining webs of neural networks. Our meticulously crafted modules transport you from the foundational stones of Python basics straight into the high towers of Theano and TensorFlow library installations.
Transition smoothly from understanding the complex labyrinths of neural structures to implementing them with flair. Whether it’s the Pima Indian Diabetes or the Iris Flower Multi-Class models, we’ll unravel the steps, terminologies, and techniques with precision. Dive deeper into the shimmering waters of Convolutional Neural Networks, where you’ll gain first-hand knowledge on data giants like the MNIST Handwritten Digit Recognition and the CIFAR-10 Object Recognition Datasets.
As the cherry on top, our Deep Learning & Neural Networks Python course does not merely offer theoretical insights. Instead, we illuminate the path to applying these neural structures in tangible scenarios. From checkpointing neural network improvements to plotting model behavior history and understanding image augmentation, every corner you turn unveils another layer of deep learning wonder. Join us in this transformative journey and sculpt your future in the AI realm.
Learning outcome
- Differentiate between machine learning and deep learning in AI projects.
- Navigate through Python basics and library installations including Theano and TensorFlow.
- Develop and evaluate models including Pima Indian Diabetes, Iris Flower Multi-Class, and more.
- Gain proficiency in convolutional neural networks with insights on MNIST and CIFAR-10 Datasets.
- Apply knowledge in practical scenarios by loading and predicting various models.
- Understand the importance and application of dropout regularization and learning rate schedules.
- Effectively use checkpointing to improve and save neural network models.
Course media
Why should I take this course?
- Comprehensive coverage of deep learning and neural networks.
- Step-by-step guide on developing and evaluating various models.
- Access to real datasets like MNIST and CIFAR-10.
- Insights on advanced concepts like dropout regularization and learning rate schedules.
- Learn how to use checkpointing to improve neural network models.
Career Path
- Data Scientist.
- Machine Learning Engineer.
- AI Research Scientist.
- Neural Network Developer.
- Deep Learning Specialist.
- Computer Vision Engineer.
Requirements
- Basic understanding of Python programming.
- Basic knowledge of machine learning concepts.
- Willingness to learn and apply new skills in deep learning.
Course Curriculum
-
Course Introduction and Table of Contents
00:11:00
-
Deep Learning Overview – Theory Session – Part 1
00:06:00
-
Deep Learning Overview – Theory Session – Part 2
00:06:00
-
Choosing Between ML or DL for the next AI project – Quick Theory Session
00:09:00
-
Preparing Your Computer – Part 1
00:07:00
-
Preparing Your Computer – Part 2
00:06:00
-
Python Basics – Assignment
00:09:00
-
Python Basics – Flow Control
00:09:00
-
Python Basics – Functions
00:04:00
-
Python Basics – Data Structures
00:12:00
-
Theano Library Installation and Sample Program to Test
00:11:00
-
TensorFlow library Installation and Sample Program to Test
00:09:00
-
Keras Installation and Switching Theano and TensorFlow Backends
00:09:00
-
Explaining Multi-Layer Perceptron Concepts
00:03:00
-
Explaining Neural Networks Steps and Terminology
00:10:00
-
First Neural Network with Keras – Understanding Pima Indian Diabetes Dataset
00:07:00
-
Explaining Training and Evaluation Concepts
00:11:00
-
Pima Indian Model – Steps Explained – Part 1
00:09:00
-
Pima Indian Model – Steps Explained – Part 2
00:07:00
-
Coding the Pima Indian Model – Part 1
00:11:00
-
Coding the Pima Indian Model – Part 2
00:09:00
-
Pima Indian Model – Performance Evaluation – Automatic Verification
00:06:00
-
Pima Indian Model – Performance Evaluation – Manual Verification
00:08:00
-
Pima Indian Model – Performance Evaluation – k-fold Validation – Keras
00:10:00
-
Pima Indian Model – Performance Evaluation – Hyper Parameters
00:12:00
-
Understanding Iris Flower Multi-Class Dataset
00:08:00
-
Developing the Iris Flower Multi-Class Model – Part 1
00:09:00
-
Developing the Iris Flower Multi-Class Model – Part 2
00:06:00
-
Developing the Iris Flower Multi-Class Model – Part 3
00:09:00
-
Understanding the Sonar Returns Dataset
00:07:00
-
Developing the Sonar Returns Model
00:10:00
-
Sonar Performance Improvement – Data Preparation – Standardization
00:15:00
-
Sonar Performance Improvement – Layer Tuning for Smaller Network
00:07:00
-
Sonar Performance Improvement – Layer Tuning for Larger Network
00:06:00
-
Understanding the Boston Housing Regression Dataset
00:07:00
-
Developing the Boston Housing Baseline Model
00:08:00
-
Boston Performance Improvement by Standardization
00:07:00
-
Boston Performance Improvement by Deeper Network Tuning
00:05:00
-
Boston Performance Improvement by Wider Network Tuning
00:04:00
-
Save & Load the Trained Model as JSON File (Pima Indian Dataset) – Part 1
00:09:00
-
Save & Load the Trained Model as JSON File (Pima Indian Dataset) – Part 2
00:08:00
-
Save and Load Model as YAML File – Pima Indian Dataset
00:05:00
-
Load and Predict using the Pima Indian Diabetes Model
00:09:00
-
Load and Predict using the Iris Flower Multi-Class Model
00:08:00
-
Load and Predict using the Sonar Returns Model
00:10:00
-
Load and Predict using the Boston Housing Regression Model
00:08:00
-
An Introduction to Checkpointing
00:06:00
-
Checkpoint Neural Network Model Improvements
00:10:00
-
Checkpoint Neural Network Best Model
00:04:00
-
Loading the Saved Checkpoint
00:05:00
-
Plotting Model Behavior History – Introduction
00:06:00
-
Plotting Model Behavior History – Coding
00:08:00
-
Dropout Regularization – Visible Layer – Part 1
00:11:00
-
Dropout Regularization – Visible Layer – Part 2
00:06:00
-
Dropout Regularization – Hidden Layer
00:06:00
-
Learning Rate Schedule using Ionosphere Dataset
00:06:00
-
Time Based Learning Rate Schedule – Part 1
00:07:00
-
Time Based Learning Rate Schedule – Part 2
00:12:00
-
Drop Based Learning Rate Schedule – Part 1
00:07:00
-
Drop Based Learning Rate Schedule – Part 2
00:08:00
-
Convolutional Neural Networks – Part 1
00:11:00
-
Convolutional Neural Networks – Part 2
00:06:00
-
Introduction to MNIST Handwritten Digit Recognition Dataset
00:06:00
-
Downloading and Testing MNIST Handwritten Digit Recognition Dataset
00:10:00
-
MNIST Multi-Layer Perceptron Model Development – Part 1
00:11:00
-
MNIST Multi-Layer Perceptron Model Development – Part 2
00:06:00
-
Convolutional Neural Network Model using MNIST – Part 1
00:13:00
-
Convolutional Neural Network Model using MNIST – Part 2
00:12:00
-
Large CNN using MNIST
00:09:00
-
Load and Predict using the MNIST CNN Model
00:14:00
-
Introduction to Image Augmentation using Keras
00:11:00
-
Augmentation using Sample Wise Standardization
00:10:00
-
Augmentation using Feature Wise Standardization & ZCA Whitening
00:04:00
-
Augmentation using Rotation and Flipping
00:04:00
-
Saving Augmentation
00:05:00
-
CIFAR-10 Object Recognition Dataset – Understanding and Loading
00:12:00
-
Simple CNN using CIFAR-10 Dataset – Part 1
00:09:00
-
Simple CNN using CIFAR-10 Dataset – Part 2
00:06:00
-
Simple CNN using CIFAR-10 Dataset – Part 3
00:08:00
-
Train and Save CIFAR-10 Model
00:08:00
-
Load and Predict using CIFAR-10 CNN Model
00:16:00
-
Recomended Readings – Deep Learning & Neural Networks Python – Keras
Offer Ends in

-
Duration:11 hours, 9 minutes
-
Access:1 Year
-
Units:82

