I
Ian Fischer
Researcher at Google
Publications - 59
Citations - 7799
Ian Fischer is an academic researcher from Google. The author has contributed to research in topics: Information bottleneck method & Computer science. The author has an hindex of 23, co-authored 53 publications receiving 6155 citations. Previous affiliations of Ian Fischer include University of California & Harvard University.
Papers
More filters
Proceedings ArticleDOI
Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors
Jonathan Huang,Vivek Rathod,Chen Sun,Menglong Zhu,Anoop Korattikara,Alireza Fathi,Ian Fischer,Zbigniew Wojna,Yang Song,Sergio Guadarrama,Kevin Murphy +10 more
TL;DR: A unified implementation of the Faster R-CNN, R-FCN and SSD systems is presented and the speed/accuracy trade-off curve created by using alternative feature extractors and varying other critical parameters such as image size within each of these meta-architectures is traced out.
Posted Content
Deep Variational Information Bottleneck
TL;DR: It is shown that models trained with the VIB objective outperform those that are trained with other forms of regularization, in terms of generalization performance and robustness to adversarial attack.
Proceedings Article
Learning Latent Dynamics for Planning from Pixels
Danijar Hafner,Timothy P. Lillicrap,Ian Fischer,Ruben Villegas,David Ha,Honglak Lee,James Davidson +6 more
TL;DR: The Deep Planning Network (PlaNet) is proposed, a purely model-based agent that learns the environment dynamics from images and chooses actions through fast online planning in latent space using a latent dynamics model with both deterministic and stochastic transition components.
Proceedings Article
Deep Variational Information Bottleneck
TL;DR: Deep Variational Information Bottleneck (Deep VIB) as discussed by the authors is a variational approximation to the information bottleneck of Tishby et al. This variational approach allows us to parameterize the bottleneck model using a neural network and leverage the reparameterization trick for efficient training.
Proceedings ArticleDOI
The Emperor's New Security Indicators
TL;DR: The first empirical evidence that role playing affects participants' security behavior is contributed: role-playing participants behaved significantly less securely than those using their own passwords.