Eric Frank
6 Papers
Eric Frank is an academic researcher. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 6, co-authored 6 publications.
Chat about Author
Papers
•Proceedings Article
An intriguing failing of convolutional neural networks and the CoordConv solution
Rosanne Liu,Joel Lehman,Piero Molino,Felipe Petroski Such,Eric Frank,Alex Sergeev,Jason Yosinski +6 more
- 01 Jan 2018
TL;DR: CoordConv as discussed by the authors proposes to give convolution access to its own input coordinates through the use of extra coordinate channels, allowing networks to learn either complete translation invariance or varying degrees of translation dependence, as required by the end task.
•Posted Content
Plug and Play Language Models: A Simple Approach to Controlled Text Generation
Sumanth Dathathri,Andrea Madotto,Janice Lan,Jane Hung,Eric Frank,Piero Molino,Jason Yosinski,Rosanne Liu +7 more
TL;DR: The Plug and Play Language Model (PPLM) for controllable language generation is proposed, which combines a pretrained LM with one or more simple attribute classifiers that guide text generation without any further training of the LM.
640
•Posted Content
An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution
Rosanne Liu,Joel Lehman,Piero Molino,Felipe Petroski Such,Eric Frank,Alex Sergeev,Jason Yosinski +6 more
TL;DR: Preliminary evidence that swapping convolution for CoordConv can improve models on a diverse set of tasks is shown, which works by giving convolution access to its own input coordinates through the use of extra coordinate channels without sacrificing the computational and parametric efficiency of ordinary convolution.
528
•Proceedings Article
Metropolis-Hastings Generative Adversarial Networks
Ryan Turner,Jane Hung,Eric Frank,Yunus Saatchi,Jason Yosinski +4 more
- 24 May 2019
TL;DR: The Metropolis-Hastings generative adversarial network (MH-GAN), which combines aspects of Markov chain Monte Carlo and GANs, is introduced, which uses the discriminator from GAN training to build a wrapper around the generator for improved sampling.
•Posted Content
Metropolis-Hastings Generative Adversarial Networks
TL;DR: The Metropolis-Hastings Generative Adversarial Network (MH-GAN) as mentioned in this paper uses the discriminator from GAN training to build a wrapper around the generator for improved sampling.
11