TensorFlow: A system for large-scale machine learning
Citations
7,624 citations
2,097 citations
1,612 citations
1,443 citations
947 citations
References
44,703 citations
"TensorFlow: A system for large-scal..." refers background or methods in this paper
...3 million floating-point parameters to classify images into one of 1000 categories [26]....
[...]
...In these experiments, we focus on Google’s Inception-v3 model, which achieves 78.8% accuracy the ILSVRC 2012 image classification challenge [70]; the same techniques apply to other deep convolutional models—such as Microsoft’s ResNet [26]—that TensorFlow users have implemented....
[...]
...8% accuracy the ILSVRC 2012 image classification challenge [70]; the same techniques apply to other deep convolutional models—such as Microsoft’s ResNet [26]—that TensorFlow users have implemented....
[...]
38,211 citations
"TensorFlow: A system for large-scal..." refers background in this paper
...Extensibility Single-machine machine learning frameworks [36, 2, 17] have extensible programming models that enable their users to advance the state of the art with new approaches, such as adversarial learning [25] and deep reinforcement learning [51]....
[...]
30,811 citations
23,814 citations
"TensorFlow: A system for large-scal..." refers methods in this paper
...A distributed system for model training must use the network efficiently....
[...]
23,074 citations
"TensorFlow: A system for large-scal..." refers background or methods in this paper
...We attribute this success to the invention of more sophisticated machine learning models [42, 51], the availability of large datasets for tackling problems in these fields [10, 65], and the development of software platforms that enable the easy use of large amounts of computational resources for…...
[...]
...We seek a system that provides the same ability to experiment, and also allows users to scale up the same code to run in production....
[...]