Neural Networks, TensorFlow, ANN, CNN, RNN, LSTM, Transfer Learning and Much More
What you will learn
The basics of Python programming language
Foundational concepts of deep learning and neural networks
How to build a neural network from scratch using Python
Advanced techniques in deep learning using TensorFlow 2.0
Convolutional neural networks (CNNs) for image classification and object detection
Recurrent neural networks (RNNs) for sequential data such as time series and natural language processing
Generative adversarial networks (GANs) for generating new data samples
Transfer learning in deep learning
Reinforcement learning and its applications in AI
Deployment options for deep learning models
Applications of deep learning in AI, such as computer vision, natural language processing, and speech recognition
The current and future trends in deep learning and AI, as well as ethical and societal implications.
Description
This comprehensive course covers the latest advancements in deep learning and artificial intelligence using Python. Designed for both beginner and advanced students, this course teaches you the foundational concepts and practical skills necessary to build and deploy deep learning models.
Module 1: Introduction to Python and Deep Learning
- Overview of Python programming language
- Introduction to deep learning and neural networks
Module 2: Neural Network Fundamentals
- Understanding activation functions, loss functions, and optimization techniques
- Overview of supervised and unsupervised learning
Module 3: Building a Neural Network from Scratch
- Hands-on coding exercise to build a simple neural network from scratch using Python
Module 4: TensorFlow 2.0 for Deep Learning
- Overview of TensorFlow 2.0 and its features for deep learning
- Hands-on coding exercises to implement deep learning models using TensorFlow
Module 5: Advanced Neural Network Architectures
- Study of different neural network architectures such as feedforward, recurrent, and convolutional networks
- Hands-on coding exercises to implement advanced neural network models
Module 6: Convolutional Neural Networks (CNNs)
- Overview of convolutional neural networks and their applications
- Hands-on coding exercises to implement CNNs for image classification and object detection tasks
Module 7: Recurrent Neural Networks (RNNs)
- Overview of recurrent neural networks and their applications
- Hands-on coding exercises to implement RNNs for sequential data such as time series and natural language processing
By the end of this course, you will have a strong understanding of deep learning and its applications in AI, and the ability to build and deploy deep learning models using Python and TensorFlow 2.0. This course will be a valuable asset for anyone looking to pursue a career in AI or simply expand their knowledge in this exciting field.
English
language
Content
Course Setup
Jupyter Notebook Introduction
Python for Deep Learning
Python Introduction Part 1
Python Introduction Part 2
Python Introduction Part 3
Numpy Introduction Part 1
Numpy Introduction Part 2
Pandas Introduction
Matplotlib Introduction Part 1
Matplotlib Introduction Part 2
Seaborn Introduction Part 1
Seaborn Introduction Part 2
Introduction to Machine Learning
Classical Machine Learning Introduction
Logistic Regression
Support Vector Machine – SVM
Decision Tree
Random Forest
L2 Regularization
L1 Regularization
Model Evaluation
ROC-AUC Curve
Code Along in Python Part 1
Code Along in Python Part 2
Code Along in Python Part 3
Code Along in Python Part 4
Introduction to Deep Learning and TensorFlow
Machine Learning Process Introduction
Types of Machine Learning
Supervised Learning
Unsupervised Learning
Reinforcement Learning
What is Deep Learning and ML
What is Neural Network
How Deep Learning Process Works
Application of Deep Learning
Deep Learning Tools
MLops with AWS
End to End Deep Learning Project
What is Neuron
Multi-Layer Perceptron
Shallow vs Deep Neural Networks
Activation Function
What is Back Propagation
Optimizers in Deep Learning
Steps to Build Neural Network
Customer Churn Dataset Loading
Data Visualization Part 1
Data Visualization Part 2
Data Preprocessing
Import Neural Networks APIs
How to Get Input Shape and Class Weights
Neural Network Model Building
Model Summary Explanation
Model Training
Model Evaluation
Model Save and Load
Prediction on Real-Life Data
Introduction to Computer Vision with Deep Learning
Introduction to Computer Vision with Deep Learning
5 Steps of Computer Vision Model Building
Fashion MNIST Dataset Download
Fashion MNIST Dataset Analysis
Train Test Split for Data
Deep Neural Network Model Building
Model Summary and Training
Discovering Overfitting – Early Stopping
Model Save and Load for Prediction
Introduction to Convolutional Neural Networks [Theory and Intuitions]
What is Convolutional Neural Network?
Working Principle of CNN
Convolutional Filters
Feature Maps
Padding and Strides
Pooling Layers
Activation Function
Dropout
CNN Architectures Comparison
LeNet-5 Architecture Explained
AlexNet Architecture Explained
GoogLeNet (Inception V1) Architecture Explained
RestNet Architecture Explained
MobileNet Architecture Explained
EfficientNet Architecture Explained
Horses vs Humans Classification with Simple CNN
Overview of Image Classification using CNNs
Introduction to TensorFlow Datasets (TFDS)
Download Humans or Horses Dataset Part 1
Download Humans or Horses Dataset Part 2
Use of Image Data Generator
Data Display in Subplots Matrix
CNN Introduction
Building CNN Model
CNN Parameter Calculation
CNN Parameter Calculations Part 2
CNN Parameter Calculations Part 3
Model Training
Model Load and Save
Image Class Prediction
Building Cats and Dogs Classifier with Regularized CNN
What is Overfitting
L1, L2 and Early Stopping Regularization
How Dropout and Batch Normalization Prevents Overfitting
What is Data Augmentation [Theory]
Sample Data Load with ImageDataGenerator for Augmentation
Random Rotation Augmentation
Random Shift Augmentation
Other Types of Data Augmentation
All Types of Augmentation at Once
TensorFlow TFDS and Cats vs Dogs Data Download
Store Data in Local Directory
Load Dataset for Baseline Classifier
Building Baseline CNN Classifier
How to Calculate Size of Output Layers of CNN and MaxPool
How to Calculate Number of Parameters in CNN and FCN
Model Training and Layers Analysis
Model Training and Validation Accuracy Plot
Building Dataset for Regularized CNN
Regularized CNN Model Building and Training
Training Log Analysis
Load Model and Do the Prediction
CNN Model Visualization
Flowers Classification with Transfer Learning and CNN
Transfer Learning Introduction
Load Flowers Dataset for Classification
Download Flowers Data
Flowers Data Visualization
Preparing Data with Image Data Generator
Baseline CNN Model Building
How to Calculate Number of Parameters in CNN
Baseline CNN Model Training
Train Model with TFDS Data Without Saving Locally Part 1
Train Model with TFDS Data Without Saving Locally Part 2
import VGG16 from Keras
Data Augmentation for Training
Make CNN Model with VGG16 Transfer Learning
Model Training for Better Accuracy
Train Any Model for Transfer Learning
Save and Load Model with Class Names
Online Prediction of Flowers Classes
Introduction to NLP
Introduction to NLP
What are Key NLP Techniques
Overview of NLP Tools
Common Challenges in NLP
Bag of Words – The Simples Word Embedding Technique
Term Frequency – Inverse Document Frequency (TF-IDF)
Load Spam Dataset
Text Preprocessing
Feature Engineering
Pair Plot
Train Test Split
TF-IDF Vectorization
Model Evaluation and Prediction on Real Data
Model Load and Store