Book Image

Machine Learning Solutions

Book Image

Machine Learning Solutions

Overview of this book

Machine learning (ML) helps you find hidden insights from your data without the need for explicit programming. This book is your key to solving any kind of ML problem you might come across in your job. You’ll encounter a set of simple to complex problems while building ML models, and you'll not only resolve these problems, but you’ll also learn how to build projects based on each problem, with a practical approach and easy-to-follow examples. The book includes a wide range of applications: from analytics and NLP, to computer vision domains. Some of the applications you will be working on include stock price prediction, a recommendation engine, building a chat-bot, a facial expression recognition system, and many more. The problem examples we cover include identifying the right algorithm for your dataset and use cases, creating and labeling datasets, getting enough clean data to carry out processing, identifying outliers, overftting datasets, hyperparameter tuning, and more. Here, you'll also learn to make more timely and accurate predictions. In addition, you'll deal with more advanced use cases, such as building a gaming bot, building an extractive summarization tool for medical documents, and you'll also tackle the problems faced while building an ML model. By the end of this book, you'll be able to fine-tune your models as per your needs to deliver maximum productivity.
Table of Contents (19 chapters)
Machine Learning Solutions
Foreword
Contributors
Preface
Index

Summary


In this chapter, we referred to a different dataset in order to make a chatbot. You learned about the rule-based approach that can be used if you don't have any datasets. You also learned about the open and closed domains. After that, we used the retrieval-based approach in order to build the basic version of a chatbot. In the revised approach, we used TensorFlow. This revised approach is great for us because it saves time compared to the basic approach. We implemented Google's neural Conversational Model paper on the Cornell Movie-Dialogs dataset. For the best approach, we built a model that used the Facebook bAbI dataset and built the basic reasoning functionality that helped us generate good results for our chatbot. Although the training time for the revised and best approaches are really long, those who want to train the model on the cloud platform can choose to do so. So far, I like Amazon Web Services (AWS) and the Google Cloud platform. I also uploaded a pre-trained model...