TensorFlow (Beginner): Avoid Overfitting Using Regularization

In this course, we will learn how to avoid overfitting by using two common regularization techniques: Weight Regularization and Dropouts. We will see how to apply these techniques with TensorFlow.

Attend for $39.99 $19.99
TensorFlow (Beginner): Avoid Overfitting Using Regularization

Duration (mins)

Learners

5.0 / 5

Rating

Task List


We will cover the following tasks in 1 hour and 13 minutes:


Introduction

  • A look at what we will create in this course.
  • Overview of the development environment in the virtual machine.

Introduction

What is Overfitting?

  • Understanding overfitting.
  • Common approaches to avoiding overfitting.
  • Understanding the problem.
  • Importing tensorflow, keras and helper libraries.

What is Overfitting?

Dataset

  • Downloading the IMDB movie reviews dataset.
  • Multi hot encoding the data.
  • A look at the encoded data.

Dataset

Creating the Baseline Model

  • Creating and compiling a baseline model.
  • Understanding loss function and optimizer.
  • A look at the model summary.

Creating the Baseline Model

Creating Model Variants

  • Creating and compiling a new model with smaller than baseline architecture.
  • Creating and compiling a new model with bigger than baseline architecture.
  • Training all three models.

Creating Model Variants

Plot History Function

  • How the plot_history function will work

Plot History Function

Plotting the Training and Validation Loss

  • Plotting the training and validation loss for the three models.
  • Demonstrating overfitting.

Plotting the Training and Validation Loss

Weight Regularization

  • Understanding regularization.
  • Two types of weight regularization.
  • Creating, compiling and training a new model with weight regularization.
  • Plotting the training and validation loss for the new model.

Weight Regularization

L2 Model vs Baseline

  • Plotting the validation and training loss for L2 model and compare it with the baseline model.

L2 Model vs Baseline

Dropouts

  • Understanding dropouts.
  • Creating, compiling and training a new model with dropouts.
  • Plotting the training and validation loss for the new model.

Dropouts

Dropout Model vs Baseline

  • Plotting the validation and training loss for Dropout model and compare it with the baseline model.

Dropout Model vs Baseline

Ready to join this 1 hour and 13 minutes session?

Amit Yadav

About the Host (Amit Yadav)


I have been writing code since 1993, when I was 11, and my first passion project started with a database management software that I wrote for a local hospital. More recently, I wrote an award winning education Chatbot for a multi-billion-revenue company. I solved a recurrent problem for my client where they wanted to make basic cyber safety and privacy education accessible for their users. This bot enabled my client to reach out to their customers with personalised and real-time education. In the last one year, I’ve continued my interest in this field by constantly learning and growing in Machine Learning, NLP and Deep Learning. I'm very excited to share my variety of experience and learnings with you with the help of Rhyme.com.



Frequently Asked Questions


In Rhyme, all sessions are completely hands on. You don't just passively watch someone else. You use the software directly while following the host's (Amit Yadav) instructions. Using the software is the only way to achieve mastery. With the "Live Guide" option, you can ask for help and get immediate response.
Nothing! Just join through your web browser. Your host (Amit Yadav) has already installed all required software and configured all data.
You can go to https://rhyme.com/for-companies, sign up for free, and follow this visual guide How to use Rhyme to create your own sessions. If you have custom needs or company-specific environment, please email us at help@rhyme.com
Absolutely. We offer Rhyme for workgroups as well larger departments and companies. Universities, academies, and bootcamps can also buy Rhyme for their settings. You can select sessions and trainings that are mission critical for you and, as well, author your own that reflect your own needs and tech environments. Please email us at help@rhyme.com
Please email us at help@rhyme.com and we'll respond to you within one business day.

Ready to join this 1 hour and 13 minutes session?