Introduction to deep learning for engineers : using Python and Google Cloud Platform / Tariq M. Arif.
Material type:
Item type | Current library | Call number | Status | Date due | Barcode |
---|---|---|---|---|---|
![]() |
Indian Institute of Technology Delhi - Central Library | Available |
Mode of access: World Wide Web.
System requirements: Adobe Acrobat Reader.
Part of: Synthesis digital library of engineering and computer science.
Includes bibliographical references (pages 87-92).
1. Introduction : Python and array operations -- 1.1. Introduction -- 1.2. Anaconda installation -- 1.3. Using Jupyter notebook -- 1.4. Array computing using NumPy
2. Introduction to PyTorch -- 2.1. Introduction -- 2.2. Setting up PyTorch -- 2.3. Basic PyTorch operations
3. Basic artificial neural network and architectures -- 3.1. Introduction -- 3.2. Applications -- 3.3. Neurons and activation functions -- 3.4. Minimizing the loss function -- 3.5. Gradient descent algorithm
4. Introduction to deep learning -- 4.1. Introduction -- 4.2. Convolutional neural network -- 4.3. Recurrent neural network (RNN) -- 4.4. Other deep learning models
5. Deep transfer learning -- 5.1. Introduction -- 5.2. Types of transfer learning -- 5.3. Using pre-trained networks -- 5.4. Model evaluation
6. Setting up PyTorch and Google Cloud Platform console -- 6.1. Introduction -- 6.2. Setting up a GCP account -- 6.3. Create a new project -- 6.4. Set up a VM instance -- 6.5. GPU quota request -- 6.6. VPC network -- 6.7. Setting up VM instance to run models
7. Case study : practical implementation through transfer learning -- 7.1. Problem statement -- 7.2. Data processing -- 7.3. Upload data into storage bucket -- 7.4. Transferring file to VM instance -- 7.5. Transfer learning steps -- 7.6. Transfer learning model (EfficientNet-B7) -- 7.7. Fine-tuning and training -- 7.8. Model testing -- 7.9. Conclusion.
Abstract freely available; full-text restricted to subscribers or individual document purchasers.
Compendex
INSPEC
Google scholar
Google book search
This book provides a short introduction and easy-to-follow implementation steps of deep learning using Google Cloud Platform. It also includes a practical case study that highlights the utilization of Python and related libraries for running a pre-trained deep learning model. In recent years, deep learning-based modeling approaches have been used in a wide variety of engineering domains, such as autonomous cars, intelligent robotics, computer vision, natural language processing, and bioinformatics. Also, numerous real-world engineering applications utilize an existing pre-trained deep learning model that has already been developed and optimized for a related task. However, incorporating a deep learning model in a research project is quite challenging, especially for someone who doesn't have related machine learning and cloud computing knowledge. Keeping that in mind, this book is intended to be a short introduction of deep learning basics through the example of a practical implementation case. The audience of this short book is undergraduate engineering students who wish to explore deep learning models in their class project or senior design project without having a full journey through the machine learning theories. The case study part at the end also provides a cost-effective and step-by-step approach that can be replicated by others easily.
Also available in print.
Title from PDF title page (viewed on July 30, 2020).
There are no comments on this title.