What do you think?
Rate this book
Deep Learning with Python: With Natural Language Processing
How to Use This Book
This book is for Students, data scientists, Deep Learning experts and professionals, and researchers in academia who want to understand the understanding of machine learning approaches/algorithms in practice using Python. This book presents some common machine and deep learning and associated technologies and their relationship. It will help the reader grab some important concepts.
What is Deep Learning?
Deep learning is a branch of machine learning that has its roots in mathematics, computer science, and neuroscience. Deep networks learn from data the way that babies learn from the world around them, starting with fresh eyes and gradually acquiring the skills needed to navigate novel environments.
Deep learning is used at Google today in more than 100 services, from Street View to Inbox Smart Reply and voice search. Several years ago, engineers at Google realized that they had to scale up these compute-intensive applications to cloud levels. Setting out to design a special-purpose chip for deep learning, they cleverly designed the board to fit into a hard disk drive slot in their data center racks. Google’s tensor processing unit (TPU) is now deployed on servers around the world, delivering an order-of-magnitude improvement in performance for deep learning applications.
Table of Contents
1. The Evolution of Artificial intelligence and Deep Learning
2. Overview of Deep Learning
3. The Rise of Machine Learning
4. General Introduction to Machine Learning
5. The Practical Concepts of Machine Learning
6. Artificial Intelligence using Python
7. Why We Are Interested In Machine Learning
8. Convolutional Neural Networks using Python
9. Recurrent Neural Networks using Python
10. Natural Language Processing and ChatBots using Python
11. Trends in Deep Learning
Deep Learning Frameworks & Compute
There are now many popular deep learning frameworks such as Tensorflow, PyTorch, CNTK, MXNet, and Caffe, as well as popular higher-level APIs such as Keras and Gluon. The choice of a deep learning toolkit depends on many factors, including the availability of good tutorials and existing implementations of model architectures and pretrained models, skill sets of the AI talents in the company, flexibility of the toolkit in expressing complex deep neural networks, availability of built-in helper functionalities, ability to effectively leverage both CPUs and GPUs, and ability to perform distributed training.
Note Keras is emerging as a popular deep learning library, due to its ability to provide high-level abstractions for modeling deep neural networks, and the flexibility to choose different backends (e.g., TensorFlow, CNTK, Theano).
In 2017, Facebook and Microsoft announced the ONNX open source format for deep learning models to enable data scientists to train a model in one framework but deploy it in another, for example.
Applications of Deep Learning
Some classic computer vision problems that can be tackled using deep learning, such as being able to classify images and find objects within the images. These common technical problems underlie many different end-user applications.
Many deep learning applications for computer vision surround health care and the medical realm, in subfields where doctors commonly inspect patients or test results visually, such as in dermatology, radiology, and ophthalmology.
About the Author
Narendra Mohan Mittal is the Founder and Chairman of Thesis Scientist and he is working in the field of Data Science/big data/machine learning/deep learning space.
This book is for Students, data scientists, Deep Learning experts and professionals, and researchers in academia who want to understand the understanding of machine learning approaches/algorithms in practice using Python. This book presents some common machine and deep learning and associated technologies and their relationship. It will help the reader grab some important concepts.
What is Deep Learning?
Deep learning is a branch of machine learning that has its roots in mathematics, computer science, and neuroscience. Deep networks learn from data the way that babies learn from the world around them, starting with fresh eyes and gradually acquiring the skills needed to navigate novel environments.
Deep learning is used at Google today in more than 100 services, from Street View to Inbox Smart Reply and voice search. Several years ago, engineers at Google realized that they had to scale up these compute-intensive applications to cloud levels. Setting out to design a special-purpose chip for deep learning, they cleverly designed the board to fit into a hard disk drive slot in their data center racks. Google’s tensor processing unit (TPU) is now deployed on servers around the world, delivering an order-of-magnitude improvement in performance for deep learning applications.
Table of Contents
1. The Evolution of Artificial intelligence and Deep Learning
2. Overview of Deep Learning
3. The Rise of Machine Learning
4. General Introduction to Machine Learning
5. The Practical Concepts of Machine Learning
6. Artificial Intelligence using Python
7. Why We Are Interested In Machine Learning
8. Convolutional Neural Networks using Python
9. Recurrent Neural Networks using Python
10. Natural Language Processing and ChatBots using Python
11. Trends in Deep Learning
Deep Learning Frameworks & Compute
There are now many popular deep learning frameworks such as Tensorflow, PyTorch, CNTK, MXNet, and Caffe, as well as popular higher-level APIs such as Keras and Gluon. The choice of a deep learning toolkit depends on many factors, including the availability of good tutorials and existing implementations of model architectures and pretrained models, skill sets of the AI talents in the company, flexibility of the toolkit in expressing complex deep neural networks, availability of built-in helper functionalities, ability to effectively leverage both CPUs and GPUs, and ability to perform distributed training.
Note Keras is emerging as a popular deep learning library, due to its ability to provide high-level abstractions for modeling deep neural networks, and the flexibility to choose different backends (e.g., TensorFlow, CNTK, Theano).
In 2017, Facebook and Microsoft announced the ONNX open source format for deep learning models to enable data scientists to train a model in one framework but deploy it in another, for example.
Applications of Deep Learning
Some classic computer vision problems that can be tackled using deep learning, such as being able to classify images and find objects within the images. These common technical problems underlie many different end-user applications.
Many deep learning applications for computer vision surround health care and the medical realm, in subfields where doctors commonly inspect patients or test results visually, such as in dermatology, radiology, and ophthalmology.
About the Author
Narendra Mohan Mittal is the Founder and Chairman of Thesis Scientist and he is working in the field of Data Science/big data/machine learning/deep learning space.
472 pages, Kindle Edition
Published January 1, 2019
23 people want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
No one has reviewed this book yet.