Introduction to Deep Learning with TensorFlow 2.0

Introduction to Deep Learning with TensorFlow 2.0

English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 5.5 Hours | 2.35 GB

Advanced implementation of regression model and essential tasks to be performed like feature selection in TensorFlow 2.x

In this course, you will learn advanced linear regression technique process and with this you can able to build any regression problem. Starting from

TensorFlow 2.x

Linear Regression

Gradient Descent Algorithm

With this intuition we will work on project: Customer Revenue Prediction.

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

Data Analysis & Preprocessing: Analyze customer data and draw the insights w.r.t revenue and based on the insights we will do data preprocessing. In this module you will learn the following.

Necessary Data Analysis

Multi-colinearity

Factor Analysis

Feature Engineering:

Lasso Regression

Identify optimal penalty factor

Feature Selection

Pipeline Model

Evaluation

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

What you’ll 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
Table of Contents

Introduction
1 Walk through the Course

TensorFlow Essentials
2 Introduction
3 Getting Started to Google Colab
4 Tensor Data Structure
5 TensorFlow Convert List to Tensors
6 TensorFlow Convert Numpy Array to Tensors
7 TensorFlow Constant
8 TensorFlow 1.x vs TensorFlow 2.x
9 Operators
10 TensorFlow Operators
11 Data Flow Graph
12 Google Colab Integrating to Google Drive
13 TensorBoard – Data Flow Graph
14 Second Graph
15 Dense Network Part-1
16 Dense Network Part-2
17 Assignment – 2 Question
18 Assignment -2 Solution

Fitting Linear Model (Linear Regression)
19 What you will learn
20 Linear Regression Intuition
21 Gradient Descent Algorithm
22 Linear Model Architecture – Perceptron (Neuron)
23 TensorFlow – Linear Regression, Part-1
24 TensorFlow – Linear Regression, Part-2
25 TensorFlow – Loss Function
26 TensorFlow – Gradient Descent
27 TensorFlow – Fitting Model
28 TensorFlow – Keras – Linear Regression

Project Overview
29 Project Overview

Data Analysis
30 Data and Distribution
31 Distribution part-2
32 Multicollinearity
33 Factor Analysis
34 Conclusion of Data Analysis
35 Data Preprocessing

Feature Engineering
36 Multiple Linear Regression
37 TensorFlow – Multiple Linear Regression
38 Lasso Regression – L1 Regularization
39 TensorFlow – Lasso Regression and Penalty Factor Slection
40 Feature Selection

Final Pipeline Model
41 Split data into Train and Test frames
42 Input Pipelines
43 Feature Columns
44 Training Pipeline Model
45 Save and Restore
46 Model Evaluation

BONUS
47 Bonus Lecture