Avoid Overfitting using Regularization

In this course, we will learn how to avoid overfitting by using two common regularization techniques: Weight Regularization and Dropouts.

Attend for FREE
Avoid Overfitting using Regularization

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

Watch Preview

Note: The actual session is completely hands-on where you interact with the software while watching the host's (Amit Yadav) instructions. You can preview the instructions here

Host: Amit Yadav


Amit Yadav

Ready to join this 1 hour and 13 minutes session for FREE?

Frequently Asked Questions


In Rhyme, all sessions are completely hands-on. You don't just passively watch someone else use the software. You use the software directly. While following the host's (Amit Yadav) instructions. Using the software is the only way to understand a software!
Nothing! Your host (Amit Yadav) has already installed all required software and configured all data in a virtual machine. You just join the session from a web-browser and start using the software immediately!
Absolutely! We are strong believers in "Information wants to be free."
Please go to https://rhyme.com, sign up for FREE, and get cracking! If you let us know about your session, we will even help you promote it! Email us at help@rhyme.com
Please email us at help@rhyme.com and we'll respond to you within a day!