S
Scott Reed
Researcher at Google
Publications - 57
Citations - 85613
Scott Reed is an academic researcher from Google. The author has contributed to research in topics: Artificial neural network & Reinforcement learning. The author has an hindex of 33, co-authored 56 publications receiving 63000 citations. Previous affiliations of Scott Reed include University of Michigan.
Papers
More filters
Generating Interpretable Images with Controllable Structure
Scott Reed,Aaron van den Oord,Nal Kalchbrenner,Victor Bapst,Matthew Botvinick,Nando de Freitas +5 more
TL;DR: Improved text-to-image synthesis with controllable object locations using an extension of Pixel Convolutional Neural Networks (PixelCNN) and it is shown how the model can generate images conditioned on part keypoints and segmentation masks.
Posted Content
Critic Regularized Regression
Ziyu Wang,Alexander Novikov,Konrad Zolna,Jost Tobias Springenberg,Scott Reed,Bobak Shahriari,Noah Siegel,Josh Merel,Caglar Gulcehre,Nicolas Heess,Nando de Freitas +10 more
TL;DR: In this paper, a critic-regularized regression (CRR) algorithm is proposed to learn policies from data using a form of critic regularized regression, which scales well to tasks with high-dimensional state and action spaces.
Proceedings Article
Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions
Scott Reed,Yutian Chen,Tom Le Paine,Aaron van den Oord,S. M. Ali Eslami,Danilo Jimenez Rezende,Oriol Vinyals,Nando de Freitas +7 more
TL;DR: This paper shows how 1) neural attention and 2) meta learning techniques can be used in combination with autoregressive models to enable effective few-shot density estimation on the Omniglot dataset.
Posted Content
Task-Relevant Adversarial Imitation Learning
Konrad Zolna,Scott Reed,Alexander Novikov,Sergio Gomez Colmenarejo,David Budden,Serkan Cabi,Misha Denil,Nando de Freitas,Ziyu Wang +8 more
TL;DR: This work proposes a solution to a critical problem in adversarial imitation, Task-Relevant Adversarial Imitation Learning (TRAIL), which uses a constrained optimization objective to overcome task-irrelevant features.
Posted Content
Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions
Scott Reed,Yutian Chen,Tom Le Paine,Aaron van den Oord,S. M. Ali Eslami,Danilo Jimenez Rezende,Oriol Vinyals,Nando de Freitas +7 more
TL;DR: In this article, a few-shot image density estimation model was proposed to learn visual concepts from only a handful of examples. But the model requires many thousands of gradient-based weight updates and unique image examples for training.