• Post category:StudyBullet-3
  • Reading time:10 mins read


Advanced implementation of regression modelling techniques like lasso regression in TensorFlow

What you will learn

TensorFlow 2.0

Gradient Descent Algorithm

Create Pipeline regression model in TensorFlow

Lasso Regression

Feature Selection with lasso

Programming in TensorFlow 2.0

Selection of Penalty factor lambda

Visualizing graph in TensorBoard

Neuron or Perceptron Model Architecture

Loss or Cost Function

TensorFlow Keras API

Linear Regression

Create customized model in TensorFlow

Exploratory Data Analysis

Data Preprocessing

Multiple Linear Regression in TensorFlow

Fitting Linear Model (Linear Regression)
What you will learn
Linear Regression Intuition
Gradient Descent Algorithm
Linear Model Architecture – Perceptron (Neuron)
TensorFlow – Linear Regression, Part-1
TensorFlow – Linear Regression, Part-2
TensorFlow – Loss Function
TensorFlow – Gradient Descent
TensorFlow – Fitting Model
TensorFlow – Keras – Linear Regression

Description

Welcome to the Course Introduction to Deep Learning with TensorFlow 2.0:

In this course, you will learn advanced linear regression technique process and with this, you can be able to build any regression problem. Using this you can solve real-world problems like customer lifetime value, predictive analytics, etc.

What you will Learn

路 TensorFlow 2.x

路 Google Colab


Get Instant Notification of New Courses on our Telegram channel.


路 Linear Regression

路 Gradient Descent Algorithm

路 Data Analysis

路 Regression

路 Feature Engineering and Selection with Lasso Regression.

路 Model Evaluation

All the above-mentioned techniques are explained in TensorFlow. In this course, you will work on the Project Customer Revenue (Lifetime value) Prediction using Gradient Descent Algorithm

Problem Statement: A large child education toy company that sells educational tablets and gaming systems both online and in retail stores wanted to analyze the customer data. The goal of the problem is to determine the following objective as shown below.

1. Data Analysis & Pre-processing: Analyse customer data and draw the insights w.r.t revenue and based on the insights we will do data pre-processing. In this module, you will learn the following.

1. Necessary Data Analysis

2. Multi-collinearity

3. Factor Analysis

2. Feature Engineering:

1. Lasso Regression

2. Identify the optimal penalty factor.

3. Feature Selection

3. Pipeline Model

4. Evaluation

We will start with the basics of TensorFlow 2.x to advanced techniques in it. Then we drive into intuition behind linear regression and optimization function like gradient descent.

English
language

Content

Introduction
Walk through the Course
TensorFlow Essentials
Introduction
Getting Started to Google Colab
Tensor Data Structure
Creating Tensors
TensorFlow 1.x vs TensorFlow 2.x
Operators
Data Flow Graph
Google Colab Integrating to Google Drive
TensorBoard – Data Flow Graph
Second Graph
Dense Network Part-1
Dense Network Part-2
Assignment – 2: Question
Assignment -2 : Solution
Fitting Linear Model (Linear Regression)
What you will learn
Linear Regression Intuition
Gradient Descent Algorithm
Linear Model Architecture – Perceptron (Neuron)
TensorFlow – Linear Regression, Part-1
TensorFlow – Linear Regression, Part-2
TensorFlow – Loss Function
TensorFlow – Gradient Descent
TensorFlow – Fitting Model
TensorFlow – Keras – Linear Regression
Project Overview
Project Overview
Data Analysis
Data and Distribution
Distribution part-2
Multicollinearity
Factor Analysis
Conclusion of Data Analysis
Data Preprocessing
Feature Engineering
Multiple Linear Regression
TensorFlow – Multiple Linear Regression
Lasso Regression – L1 Regularization
TensorFlow – Lasso Regression and Penalty Factor Slection
Feature Selection
Final Pipeline Model
Split data into Train and Test frames
Input Pipelines
Feature Columns
Training Pipeline Model
Save and Restore
Model Evaluation
BONUS
Bonus Lecture