Learning Deep Learning

Price:

NPR 1,426.00


Learning Deep Learning

Illuminating both the core concepts and the hands-on programming techniques needed to succeed, this text can be used for students with prior programming experince but with no prior machine learning or statistics experience.

NPR 1,426.00 1426.0 NPR NPR 1,584.00

NPR 1,584.00


  • Author
  • Pages
  • Pages 760
  • Year
  • ISBN
  • Publisher
  • Language
  • Subject
  • Edition
  • Weight
  • Dimensions
  • Binding

This combination is not available.

Share :

Learning Deep Learning

Illuminating both the core concepts and the hands-on programming techniques needed to succeed, this text can be used for students with prior programming experince but with no prior machine learning or statistics experience. After introducing the essential building blocks of deep neural networks, such as artificial neurons and fully connected, convolutional, and recurrent layers, Ekman shows how to use them to build advanced architectures, including the Transformer. He describes how these concepts are used to build modern networks for computer vision and natural language processing (NLP), including Mask R-CNN, GPT, and BERT. And he explains a natural language translator and a system generating natural language descriptions of images. Throughout, Ekman provides concise, well-annotated code examples using TensorFlow with Keras. Corresponding PyTorch examples are provided online, and the book thereby covers the two dominating Python libraries for DL used in industry and academia. He concludes with an introduction to neural architecture search (NAS), exploring important ethical issues and providing resources for further learning.

Table of Content:

1. The Rosenblatt Perceptron 
2. Gradient-Based Learning 
3. Sigmoid Neurons and Backpropagation 
4. Fully Connected Networks Applied to Multiclass Classification 
5. Fully Connected Networks Applied to Regression 
6. Toward DL: Frameworks and Network Tweaks 
7. Convolutional Neural Networks Applied to Image Classification 
8. Deeper CNNs and Pretrained Models 
9. Predicting Time Sequences with Recurrent Neural Networks 
10. Neural Language Models and Word Embeddings 
11. Sequence-to-Sequence Networks and Natural Language Translation 
12. One-to-Many Network for Image Captioning 
13. Attention and the Transformer 
14. Medley of Additional Topics 
15. Summary and Next Steps ONLINE CHAPTERS 
16. Long Short-Term Memory 
17. Text Autocompletion with LSTM and Beam Search 
18. Word Embeddings from word2vec and GloVe"

Book
Author Ekman
Pages 760
Year 2022
ISBN 9789356063976
Publisher Pearson
Language English
Uncategorized
Subject Computer Science / Artificial Intelligence (AI)
Edition 1/e
Weight 100 g
Dimensions 24.4 x 20.3 x 3.7 cm
Binding Paperback