Practical Convolutional Neural Network Models

Practical Convolutional Neural Network Models

by Pradeep Pujari

Paperback

$34.99
View All Available Formats & Editions
Choose Expedited Shipping at checkout for guaranteed delivery by Thursday, March 28

Product Details

ISBN-13: 9781788392303
Publisher: Packt Publishing
Publication date: 02/26/2018
Pages: 218
Sales rank: 1,047,786
Product dimensions: 7.50(w) x 9.25(h) x 0.46(d)

About the Author

Mohit Sewak is a Sr. Cognitive Data Scientist with IBM, and a Ph.D. scholar in AI & CS with BITS Pilani. He holds several Patents and Publications in AI, Deep Learning, and Machine Learning. He has been the Lead Data Scientist for some of the very successful global AI/ ML software and Industry solutions and had been earlier engaged with solutioning and research for Watson Cognitive Commerce product line. He has 14 years of very rich experience in architecting and solutioning with technologies like TensorFlow, Torch, Caffe, Theano, Keras, Watson and others. Md. Rezaul Karim is a Research Scientist at Fraunhofer FIT, Germany. He is also a PhD candidate at RWTH Aachen University, Germany. Before joining FIT, he worked as a Researcher at the Insight Centre for Data Analytics, Ireland. Earlier, he worked as a Lead Engineer at Samsung Electronics, Korea. He has 9 years of R&D experience with C++, Java, R, Scala, and Python. He has published several research papers concerning bioinformatics, big data, and deep learning. He has practical working experience with Spark, Zeppelin, Hadoop, Keras, Scikit-Learn, TensorFlow, DeepLearning4j, MXNet, and H2O. Pradeep Pujari is machine learning engineer at Walmart Labs and distinguished member of ACM. His core domain expertise is in information retrieval, machine learning and natural language processing. In off hours, he loves exploring AI technologies, enjoys reading and mentoring.

Table of Contents

Table of Contents

  1. Deep Neural Networks - Overview
  2. Introduction to Convolutional Neural Networks
  3. Build Your First CNN and Performance Optimization
  4. Popular CNN Model's Architectures
  5. Transfer Learning
  6. Autoencoders for CNN
  7. Object Detection with CNN
  8. Generative Adversarial Network
  9. Visual Attention Based CNN

Customer Reviews

Most Helpful Customer Reviews

See All Customer Reviews