Deep Learning with Python

By F. Chollet. 2017

2,814 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Deep Learning for IoT Big Data and Streaming Analytics: A Survey (2017, background): “Chollet [177] argued that problems requiring reasoning, long-term planning, and algorithmic-like data manipulation, cannot be solved by deep learning models.”
Deep Learning: A Critical Appraisal (2018, background): “(Chollet makes quite similar points in the closing chapters of his his (Chollet, 2017) text.)”
An End-to-End Deep Neural Network for Autonomous Driving Designed for Embedded Automotive Platforms (2019, result): “The results were compared in terms of performance, successfully driving on the representative track, and in terms of complexity of the network, a number of trainable parameters, and the size of the trained model.”
A Gentle Introduction to Deep Learning in Medical Image Processing (2018, background): “dical Physics December 24, 2018 arXiv:1810.05401v2 [cs.CV] 21 Dec 2018 tutorials and reviews [9, 10, 11, 12, 13, 14, 15, 16, 17, 18] over blog posts and jupyter notebooks [19, 20, 21] to entire books [22, 23, 24, 25]. All of them serve a dierent purpose and oer a dierent view on this quickly evolvin”
Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning (2021, background): “Furthermore, transfer learning in DL has been extensively implemented on different fields of computer vision with remarkable results and is considered suitable when the training dataset is small allowing for better performance and less computational effort [9,38].”
Grape detection, segmentation and tracking using deep neural networks and three-dimensional association (2019, methodology): “Weemployed image augmentation to mitigate overﬁtting (Chollet, 2017), adopting transformations of the original images that could simulate ﬁeld conditions: diﬀerences in lighting, camera focus, noise or dirty lenses.”
Distributed Representations of Tuples for Entity Resolution (2017, methodology): “We used Torch [14] and Keras [11], a deep learning framework, to train and test our models.”
High Quality Prediction of Protein Q8 Secondary Structure by Diverse Neural Network Architectures (2018, background): “tual feature maps [21]. This is followed by a series of cascading convolutional layers. A series of 3 concatenated 1D convolutions are applied. Each of the convolutions are followed by several layers [4]: time distributed ReLU activation, batch normalization and dropout layers (with probability 0.5)”
Convolutional Neural Networks for the Automatic Identification of Plant Diseases (2019, methodology): “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).”
Predicting changes in protein thermodynamic stability upon point mutation with deep 3D convolutional neural networks (2020, methodology): “We employed this procedure to obtain an ensemble of ten models 610 as model ensembling has been suggested to produce better predictions (67).”
Concrete material science: Past, present, and future innovations (2018, background): “On the other hand, all the spectacular advances made in speech and image recognition or in autonomous driving in the last few years are all related to deep learning [255,256].”
BirdNET: A deep learning solution for avian diversity monitoring (2021, background): “Our overall process mostly followed current best practices in deep learning which are well summarized in (Chollet, 2017).”
Survey on categorical data for neural networks (2020, unknown): “In [59] the authors perform experiments that compare their hash embedding method to the hashing method Chollet presents in [22], as well as to several other embedding methods.”