Deep Learning by TensorFlow 2.0 Basic to Advance with Python

Course Curriculum

Chapter 1: Introduction of Deep Learning and TensorFlow 2.x

Lecture 1: TensorFlow 2.x Introduction, Prerequisite and Training Content

Lecture 2: Installations , Technology , Folder structure and 1.x vs 2.x

Lecture 3: Why Deep Learning is emerging

Lecture 4: Deep-Learning-Working-components

Chapter 2: TensorFlow 2.0 Basic

Lecture 1: TensorFlow Basics code

Lecture 2: Tensor segmentation code

Lecture 3: Regression with Premade Estimators

Lecture 4: Regression by using tf.keras model layers

Lecture 5: Classifications using Premade Estimators

Lecture 6: Multiclass classification using Tensorflow Multi level

Chapter 3: TensorFlow 2.0 Intermediate

Lecture 1: Binary classification on Kaggle data using TensorFlow Multi level

Lecture 2: Explore few more ways to better classification

Lecture 3: How-to-Teach-Machines

Lecture 4: CNN-Showcase-of-multiplications

Lecture 5: Important-terms-in-Deep-Learning

Lecture 6: The-MNIST-Data

Lecture 7: CNN for Image (MNIST) classification

Lecture 8: Classwork

Lecture 9: Image Data Generator also known as Data Augmentation

Lecture 10: Image Data Generator – Data generation

Lecture 11: CNN with Image Data Generator

Lecture 12: Emotion recognition with CNNs

Lecture 13: Recurrent-Neural-Networks-Overview

Lecture 14: The-Vanishing-and-Exploding-Gradient-Overview

Lecture 15: LSTM-and-GRU-Architecture

Lecture 16: Univariate Time Series using LSTM_train_test_mode

Lecture 17: Univariate Time Series using LSTM_train_mode

Lecture 18: Multivariate Time Series using LSTM

Lecture 19: How to know models are good enough Bias vs Variance

Chapter 4: TensorFlow 2.0 Advanced

Lecture 1: Transfer learning – Definition and Usages

Lecture 2: Basic model

Lecture 3: Customize the model to recognize the classes in our dataset

Lecture 4: Use inbuilt model to recognize the classes in our dataset

Lecture 5: Customize inbuilt model to recognize the classes in our dataset

Lecture 6: How-to-avoid-Overfitting

Lecture 7: How to avoid Overfitting – L2 and L1

Lecture 8: How to avoid Overfitting -Dropout – Batch Normalization – Early Stopping

Lecture 9: Generative Adversarial Networks (GANs)

Lecture 10: Generative Adversarial Networks (GANs) – code

Lecture 11: Hyper-parameters-tuning-for-Deep-Learning-Models

Lecture 12: Hyperparameter tuning by keras tuner

Chapter 5: Miscellaneous

Lecture 1: Best-Practices-for-DL

Lecture 2: Award-winning-Architectures

Lecture 3: References-and-Updates

Chapter 6: Introduction of Deep Learning and TensorFlow 1.x

Lecture 1: TensorFlow Introduction and Prerequisite

Lecture 2: TensorFlow Training Content

Lecture 3: Deep Learning is emerging field

Lecture 4: What is TensorFlow

Lecture 5: Deep Learning – Working components

Chapter 7: Foundation of Deep Learning (TensorFlow and Keras)

Lecture 1: TensorFlow Basics code

Lecture 2: TensorFlow Placeholder code

Lecture 3: TensorFlow rank and Simple Equations

Lecture 4: Reduction and important operations

Lecture 5: TensorFlow Session

Lecture 6: Tensor segmentation

Lecture 7: TensorFlow – Various operations

Lecture 8: Eager execution

Chapter 8: TensorFlow and Keras for Regression

Lecture 1: Regression and Classifications overview

Lecture 2: Regression with Premade Estimators – code

Lecture 3: Tensorboard

Lecture 4: Regression using tf.keras model layers – code

Lecture 5: Regression by Keras

Lecture 6: linear regression using Core TensorFlow – 2 Independents only – code

Lecture 7: Core Tensorflow for multi variable regression – code

Chapter 9: TensorFlow and Keras for Classifications

Lecture 1: Classifications using Premade Estimators – code

Lecture 2: Multiclass classification using Core Tensorflow – code

Lecture 3: Multiclass classification using Tensorflow Multi level – code

Lecture 4: Multiclass classification using Keras – code

Chapter 10: Convolutional Neural Net (CNN): Image Classifications

Lecture 1: How to Teach Machines

Lecture 2: CNN Showcase of multiplications

Lecture 3: Important terms in Deep Learning

Lecture 4: The MNIST Data

Lecture 5: The MNIST Data exploration – code

Lecture 6: Using core TF for MNIST Softmax after flattening the data – code

Lecture 7: TF tf.keras model layers for MNIST Softmax after flattening the data – 1 – code

Lecture 8: TF tf.keras model layers for MNIST Softmax after flattening the data – 1 – code

Lecture 9: Building a CNN for MNIST using TF Layers without flattening the data – 1- code

Lecture 10: Building a CNN for MNIST using TF Layers without flattening the data – 2- code

Lecture 11: Keras CNN – 1- code

Lecture 12: Keras CNN – 2- code

Lecture 13: Kaggle Emotion recognition with CNNs using Keras – 1- code

Lecture 14: Kaggle Emotion recognition with CNNs using Keras – 2- code

Lecture 15: Kaggle Emotion recognition with CNNs using Keras – 3- code

Chapter 11: Recurrent Neural Networks (RNN) for Sequence data

Lecture 1: Recurrent Neural Networks – Overview

Lecture 2: The Vanishing and Exploding Gradient – Overview

Lecture 3: LSTM and GRU Architecture

Lecture 4: LSTM using Keras with train-test mode – 1 – code

Lecture 5: LSTM using Keras with train-test mode – 2 – code.mp4

Lecture 6: LSTM using Keras with train-test mode – 3 – code.mp4