Search icon CANCEL
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Machine Learning Solutions

You're reading from   Machine Learning Solutions Expert techniques to tackle complex machine learning problems using Python

Arrow left icon
Product type Paperback
Published in Apr 2018
Publisher Packt
ISBN-13 9781788390040
Length 566 pages
Edition 1st Edition
Languages
Tools
Arrow right icon
Author (1):
Arrow left icon
Jalaj Thanaki Jalaj Thanaki
Author Profile Icon Jalaj Thanaki
Jalaj Thanaki
Arrow right icon
View More author details
Toc

Table of Contents (19) Chapters Close

Machine Learning Solutions
Foreword
Contributors
Preface
1. Credit Risk Modeling 2. Stock Market Price Prediction FREE CHAPTER 3. Customer Analytics 4. Recommendation Systems for E-Commerce 5. Sentiment Analysis 6. Job Recommendation Engine 7. Text Summarization 8. Developing Chatbots 9. Building a Real-Time Object Recognition App 10. Face Recognition and Face Emotion Recognition 11. Building Gaming Bot List of Cheat Sheets Strategy for Wining Hackathons Index

The best approach


We have covered the entire concept that can help us implement the DMN-based chatbot. In order to implement this approach, we will be using Keras with the TensorFlow backend. Without wasting any time, we will jump to the implementation section. You can refer to the code for this approach using this GitHub link: https://github.com/jalajthanaki/Chatbot_based_on_bAbI_dataset_using_Keras.

Implementing the best approach

Here, we will train our model on the given bAbI task 1 dataset. First of all, we need to parse the stories and build the vocabulary. You can refer to the code in the following figure:

Figure 8.34: Code snippet for parsing stories and build vocabulary

We can initialize our model and set its loss function as a categorical cross-entropy with stochastic gradient descent implementation using RMSprop in Keras. You can refer to the following screenshot:

Figure 8.35: Code snippet for building the model

Before training, we need to set a hyperparameter. With the help of the value...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at AU $24.99/month. Cancel anytime