000			01782nam a22002177a 4500
003			IIITD
005			20250418020003.0
008			240427b |||||||| |||| 00| 0 eng d
020			_a9781617293702
040			_aIIITD
082			_a006.31 _bTRA-D
100			_aTrask, Andrew W.
245			_aGrokking deep learning _cby Andrew W. Trask.
260			_aGreenwich : _bManning, _c©2019
300			_a309 p. : _bill. ; _c24 cm.
501			_aIncluding index.
505			_tChapter 1. Introducing deep learning: why you should learn it _tChapter 2. Fundamental concepts: how do machines learn? _tChapter 3. Introduction to neural prediction: forward propagation _tChapter 4. Introduction to neural learning: gradient descent _tChapter 5. Learning multiple weights at a time: generalizing gradient descent _tChapter 6. Building your first deep neural network: introduction to backpropagation _tChapter 7. How to picture neural networks: in your head and on paper _tChapter 8. Learning signal and ignoring noise: introduction to regularization and batching _tChapter 9. Modeling probabilities and nonlinearities: activation functions _tChapter 10. Neural learning about edges and corners: intro to convolutional neural networks _tChapter 11. Neural networks that understand language: king – man + woman == ? _tChapter 12. Neural networks that write like Shakespeare: recurrent layers for variable-length data _tChapter 13. Introducing automatic optimization: let’s build a deep learning framework _tChapter 14. Learning to write like Shakespeare: long short-term memory _tChapter 15. Deep learning on unseen data: introducing federated learning _tChapter 16. Where to go from here: a brief guide
650			_aneural networks
650			_alanguage modeling
942			_2ddc _cBK _03
999			_c172610 _d172610