TensorFlow Deep Learning Projects

Author: Alexey Grigorev   rajalingappaa shanmugamani   Alberto Boschetti   Luca Massaron   Abhishek Thakur  

Publisher: Packt Publishing‎

Publication year: 2018

E-ISBN: 9781788398381

P-ISBN(Paperback): 89543100538970

Subject: TP181 automatic reasoning, machine learning

Language: ENG

Access to resources Favorite

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

TensorFlow Deep Learning Projects

Description

Luca Massaron is a data scientist and marketing research director specialized in multivariate statistical analysis, machine learning, and customer insight, with 10+ years experience of solving real-world problems and generating value for stakeholders using reasoning, statistics, data mining, and algorithms. Passionate about everything on data analysis and demonstrating the potentiality of data-driven knowledge discovery to both experts and non-experts, he believes that a lot can be achieved by understanding in simple terms and practicing the essentials of any discipline. Alberto Boschetti is a data scientist with strong expertise in signal processing and statistics. He holds a PhD in telecommunication engineering and lives and works in London. In his work, he faces daily challenges spanning natural language processing, machine learning, and distributed processing. He is very passionate about his job and always tries to stay up to date on the latest development in data science technologies, attending meetups, conferences, and other events. Alexey Grigorev is a skilled data scientist, machine learning engineer, and software developer with more than 8 years of professional experience. He started his career as a Java developer working at a number of large and small companies, but after a while he switched to data science. Right now, Alexey works as a data scientist at Simplaex, where, in his day-to-day job, he actively uses Java and Python for data cleaning, data analysis, and modeling. His areas of expertise are machine learning and text mining. Abhishek Thakur is a data scientist. His focus is mainly on applied machine learning and deep learning, rather than theoretical aspects. He completed his master's in computer science at the University of Bonn in early 2014. Since then, he has worked in various industries, with a research focus on automatic machine learning. He likes taking part in machine learning competitions and has attained a third place in the worldwide rankings on the popular website Kaggle. Rajalingappaa Shanmugamani is currently a deep learning lead at SAP, Singapore. Previously, he worked and consulted at various startups, developing computer vision products. He has a master's from IIT Madras, his thesis having been based on the applications of computer vision in manufacturing. He has published articles in peer-reviewed journals, and spoken at conferences, and applied for a few patents in machine learning. In his spare time, he coaches programming and machine learning to school students and engineers.

Chapter

Train the model and make predictions

Follow-up questions

Summary

Chapter 2: Annotating Images with Object Detection API

The Microsoft common objects in context

The TensorFlow object detection API

Grasping the basics of R-CNN, R-FCN and  SSD models

Presenting our project plan

Setting up an environment suitable for the project

Protobuf compilation

Windows installation

Unix installation

Provisioning of the project code

Some simple applications

Real-time webcam detection

Acknowledgements

Summary

Chapter 3: Caption Generation for Images

What is caption generation?

Exploring image captioning datasets

Downloading the dataset

Converting words into embeddings

Image captioning approaches

Conditional random field

Recurrent neural network on convolution neural network

Caption ranking

Dense captioning

RNN captioning

Multimodal captioning

Attention-based captioning

Implementing a caption generation model

Summary

Chapter 4: Building GANs for Conditional Image Creation

Introducing GANs

The key is in the adversarial approach

A cambrian explosion

DCGANs

Conditional GANs

The project

Dataset class

CGAN class

Putting CGAN to work on some examples

MNIST

Zalando MNIST

EMNIST

Reusing the trained CGANs

Resorting to Amazon Web Service

Acknowledgements

Summary

Chapter 5: Stock Price Prediction with LSTM

Input datasets – cosine and stock price

Format the dataset

Using regression to predict the future prices of a stock

Long short-term memory – LSTM 101

Stock price prediction with LSTM

Possible follow - up questions

Summary

Chapter 6: Create and Train Machine Translation Systems

A walkthrough of the architecture

Preprocessing of the corpora

Training the machine translator

Test and translate

Home assignments

Summary

Chapter 7: Train and Set up a Chatbot, Able to Discuss Like a Human

Introduction to the project

The input corpus

Creating the training dataset

Training the chatbot

Chatbox API

Home assignments

Summary

Chapter 8: Detecting Duplicate Quora Questions

Presenting the dataset

Starting with basic feature engineering

Creating fuzzy features

Resorting to TF-IDF and SVD features

Mapping with Word2vec embeddings

Testing machine learning models

Building a TensorFlow model

Processing before deep neural networks

Deep neural networks building blocks

Designing the learning architecture

Summary

Chapter 9: Building a TensorFlow Recommender System

Recommender systems

Matrix factorization for recommender systems

Dataset preparation and baseline

Matrix factorization

Implicit feedback datasets

SGD-based matrix factorization

Bayesian personalized ranking

RNN for recommender systems

Data preparation and baseline

RNN recommender system in TensorFlow

Summary

Chapter 10: Video Games by Reinforcement Learning

The game legacy

The OpenAI version

Installing OpenAI on Linux (Ubuntu 14.04 or 16.04)

Lunar Lander in OpenAI Gym

Exploring reinforcement learning through deep learning

Tricks and tips for deep Q-learning

Understanding the limitations of deep Q-learning

Starting the project

Defining the AI brain

Creating memory for experience replay

Creating the agent

Specifying the environment

Running the reinforcement learning process

Acknowledgements

Summary

Other Books You May Enjoy

Index

The users who browse this book also browse