Learning Deep 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"
|
Salient Features
">> All students need to get started, and get result, sno machine learning background required. >> Packed with clear, thorough explanations and concise, well-annotated code examples. >> Presents an extensive set of code examples built with TensorFlow and the Keras API, with complementary PyTorch examples provided online. >> Thoroughly demonstrates the use of deep learning in an advanced image captioning network application that combines image and language processing. >> Straight from NVIDIA, creator of the GPU hardware that brings deep learning models to life."
|
|
|
|
|