Section 1 : Introduction
|
Lecture 1 | Welcome to the course | 00:02:14 Duration |
|
Lecture 2 | Introduction to Neural Networks and Course flow | 00:04:39 Duration |
|
Lecture 3 | Course Resources |
Section 2 : Setting up Python and Jupyter Notebook
|
Lecture 1 | Installing Python and Anaconda | 00:03:04 Duration |
|
Lecture 2 | Opening Jupyter Notebook | 00:09:06 Duration |
|
Lecture 3 | Introduction to Jupyter | 00:13:27 Duration |
|
Lecture 4 | Arithmetic operators in Python Python Basics | 00:04:28 Duration |
|
Lecture 5 | Strings in Python Python Basics | 00:19:07 Duration |
|
Lecture 6 | Lists, Tuples and Directories Python Basics | 00:18:41 Duration |
|
Lecture 7 | Working with Numpy Library of Python | 00:11:55 Duration |
|
Lecture 8 | Working with Pandas Library of Python | 00:09:15 Duration |
|
Lecture 9 | Working with Seaborn Library of Python | 00:08:58 Duration |
Section 3 : Single Cells - Perceptron and Sigmoid Neuron
|
Lecture 1 | Perceptron | 00:09:47 Duration |
|
Lecture 2 | Activation Functions | 00:07:31 Duration |
|
Lecture 3 | Python - Creating Perceptron model | 00:14:11 Duration |
Section 4 : Neural Networks - Stacking cells to create network
|
Lecture 1 | Basic Terminologies | 00:09:47 Duration |
|
Lecture 2 | Gradient Descent | |
|
Lecture 3 | Back Propagation | 00:22:27 Duration |
Section 5 : Important concepts Common Interview questions
|
Lecture 1 | Some Important Concepts | 00:12:44 Duration |
Section 6 : Standard Model Parameters
|
Lecture 1 | Hyperparameters | 00:08:19 Duration |
Section 7 : Practice Test
|
Lecture 1 | About Proctor Testing |
Section 8 : Tensorflow and Keras
|
Lecture 1 | Keras and Tensorflow | |
|
Lecture 2 | Installing Tensorflow and Keras | 00:04:04 Duration |
Section 9 : Python - Dataset for classification problem
|
Lecture 1 | Dataset for classification | 00:07:20 Duration |
|
Lecture 2 | Normalization and Test-Train split | 00:06:00 Duration |
|
Lecture 3 | More about test-train split |
Section 10 : Python - Building and training the Model
|
Lecture 1 | Different ways to create ANN using Keras | 00:01:59 Duration |
|
Lecture 2 | Building the Neural Network using Keras | 00:12:19 Duration |
|
Lecture 3 | Compiling and Training the Neural Network model | 00:10:34 Duration |
|
Lecture 4 | Evaluating performance and Predicting using Keras | 00:09:21 Duration |
Section 11 : Python - Solving a Regression problem using ANN
|
Lecture 1 | Building Neural Network for Regression Problem | 00:22:11 Duration |
Section 12 : Complex ANN Architectures using Functional API
|
Lecture 1 | Using Functional API for complex architectures | 00:12:41 Duration |
Section 13 : Saving and Restoring Models
|
Lecture 1 | Saving - Restoring Models and Using Callbacks | 00:19:49 Duration |
Section 14 : Hyperparameter Tuning
|
Lecture 1 | Hyperparameter Tuning | 00:09:06 Duration |
Section 15 : Add-on 1 Data Preprocessing
Section 16 : Add-on 2 Classic ML models - Linear Regression
|
Lecture 1 | The Problem Statement | 00:01:26 Duration |
|
Lecture 2 | Basic Equations and Ordinary Least Squares (OLS) method | 00:08:13 Duration |
|
Lecture 3 | Assessing accuracy of predicted coefficients | 00:14:40 Duration |
|
Lecture 4 | Assessing Model Accuracy RSE and R squared | 00:07:20 Duration |
|
Lecture 5 | Simple Linear Regression in Python | |
|
Lecture 6 | Multiple Linear Regression | 00:04:58 Duration |
|
Lecture 7 | The F - statistic | 00:08:22 Duration |
|
Lecture 8 | Interpreting results of Categorical variables | 00:05:04 Duration |
|
Lecture 9 | Multiple Linear Regression in Python | 00:14:13 Duration |
|
Lecture 10 | Test-train split | 00:09:32 Duration |
|
Lecture 11 | Bias Variance trade-off | 00:06:02 Duration |
|
Lecture 12 | Test train split in Python | 00:10:19 Duration |