Felipe Petroski Such

verfied profile

∙ 0 followers
Rochester Institute of Technology ∙ Uber

Featured Co-authors

Rui Wang
167 publications
Chao Zhang
104 publications
Jeff Clune
42 publications
Kenneth O. Stanley
28 publications
Jason Yosinski
24 publications
Joel Lehman
23 publications
Theofanis Karaletsos
16 publications
Pablo Samuel Castro
15 publications
Piero Molino
14 publications
Rosanne Liu
8 publications
Raymond Ptucha
7 publications

Synthetic Petri Dish: A Novel Surrogate Model for Rapid Architecture Search

Neural Architecture Search (NAS) explores a large space of architectural...
05/27/2020 ∙ by Aditya Rawal, et al. ∙ 18 ∙ share

read it
Generalized Hidden Parameter MDPs Transferable Model-based RL in a Handful of Trials

There is broad interest in creating RL agents that can solve many (relat...
02/08/2020 ∙ by Christian F. Perez, et al. ∙ 0 ∙ share

read it
Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data

This paper investigates the intriguing question of whether we can create...
12/17/2019 ∙ by Felipe Petroski Such, et al. ∙ 36 ∙ share

read it
Fully Convolutional Networks for Handwriting Recognition

Handwritten text recognition is challenging because of the virtually inf...
07/10/2019 ∙ by Felipe Petroski Such, et al. ∙ 0 ∙ share

read it
An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents

Much human and computational effort has aimed to improve how deep reinfo...
12/17/2018 ∙ by Felipe Petroski Such, et al. ∙ 6 ∙ share

read it
Efficient transfer learning and online adaptation with latent variable models for continuous control

Traditional model-based RL relies on hand-specified or learned models of...
12/08/2018 ∙ by Christian F. Perez, et al. ∙ 0 ∙ share

read it
An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution

Few ideas have enjoyed as large an impact on deep learning as convolutio...
07/09/2018 ∙ by Rosanne Liu, et al. ∙ 6 ∙ share

read it
Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning

Deep artificial neural networks (DNNs) are typically trained via gradien...
12/18/2017 ∙ by Felipe Petroski Such, et al. ∙ 0 ∙ share

read it
Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents

Evolution strategies (ES) are a family of black-box optimization algorit...
12/18/2017 ∙ by Edoardo Conti, et al. ∙ 0 ∙ share

read it
Robust Spatial Filtering with Graph Convolutional Neural Networks

Convolutional Neural Networks (CNNs) have recently led to incredible bre...
03/02/2017 ∙ by Felipe Petroski Such, et al. ∙ 0 ∙ share

read it