Deep Learning with Python
Citations
903 citations
779 citations
Cites background from "Deep Learning with Python"
...A partial list includes Brenden Lake and Marco Baroni (2017), François Chollet (2017), Robin Jia and Percy Liang (2017), Dileep George and others at Vicarious (Kansky et al., 2017) and Pieter Abbeel and colleagues at Berkeley (Stoica et al., 2017)....
[...]
...(Chollet makes quite similar points in the closing chapters of his his (Chollet, 2017) text.)...
[...]
...Yet deep learning may well be approaching a wall, much as I anticipated earlier, at beginning of the resurgence (Marcus, 2012), and as leading figures like Hinton (Sabour, Frosst, & Hinton, 2017) and Chollet (2017) have begun to imply in recent months....
[...]
...I thank Christina 1 Chen, François Chollet, Ernie Davis, Zack Lipton, Stefano Pacifico, Suchi Saria, and Athena Vouloumanos for sharp-eyed comments, all generously supplied on short notice during the holidays at the close of 2017....
[...]
...François Chollet, Google, author of Keras neural network library December 18, 2017 ‘Science progresses one funeral at a time....
[...]
222 citations
Cites background from "Deep Learning with Python"
...Due to the good readability of Python’s syntax, the convenience and easy access for machine learning and data mining newcomers is increased (Chollet, 2018)....
[...]
186 citations
Cites background or methods from "Deep Learning with Python"
...This means that information about the validation data indirectly leaks into the model, resulting in an artificial ability to perform well on these images (Chollet, 2017)....
[...]
...Fine-tuning consists in using the weights of a pre-trained model to initialize the model and then training all or part of these weights on the target dataset (Chollet, 2017)....
[...]
...Secondly, the images must be normalized to help the model to converge more quickly as well as to better generalize on unseen data (Chollet, 2017)....
[...]
157 citations
Cites methods from "Deep Learning with Python"
...These two tools are powerful, as most Kaggle competition3 winners used either the XGBoost library (for shallow machine learning) or Keras (for deep learning) [33]....
[...]