Predictive Representations: Building Blocks of Intelligence
Carvalho, Wilka, Tomov, Momchil S, de Cothi, William, Barry, Caswell, Gershman, Samuel J
Published in Neural computation (11.10.2024)
Published in Neural computation (11.10.2024)
Get more information
Journal Article
Predictive representations: building blocks of intelligence
Carvalho, Wilka, Tomov, Momchil S, de Cothi, William, Barry, Caswell, Gershman, Samuel J
Year of Publication 09.02.2024
Year of Publication 09.02.2024
Get full text
Journal Article
Feature-Attending Recurrent Modules for Generalization in Reinforcement Learning
Carvalho, Wilka, Lampinen, Andrew, Nikiforou, Kyriacos, Hill, Felix, Shanahan, Murray
Year of Publication 15.12.2021
Year of Publication 15.12.2021
Get full text
Journal Article
Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning
Hoang, Christopher, Sohn, Sungryull, Choi, Jongwook, Carvalho, Wilka, Lee, Honglak
Year of Publication 18.11.2021
Year of Publication 18.11.2021
Get full text
Journal Article
Composing Task Knowledge with Modular Successor Feature Approximators
Carvalho, Wilka, Filos, Angelos, Lewis, Richard L, lee, Honglak, Singh, Satinder
Year of Publication 28.01.2023
Year of Publication 28.01.2023
Get full text
Journal Article
Combining Behaviors with the Successor Features Keyboard
Carvalho, Wilka, Saraiva, Andre, Filos, Angelos, Lampinen, Andrew Kyle, Matthey, Loic, Lewis, Richard L, Lee, Honglak, Singh, Satinder, Rezende, Danilo J, Zoran, Daniel
Year of Publication 24.10.2023
Year of Publication 24.10.2023
Get full text
Journal Article
Reinforcement Learning for Sparse-Reward Object-Interaction Tasks in a First-person Simulated 3D Environment
Carvalho, Wilka, Liang, Anthony, Lee, Kimin, Sohn, Sungryull, Lee, Honglak, Lewis, Richard L, Singh, Satinder
Published in arXiv.org (20.05.2021)
Published in arXiv.org (20.05.2021)
Get full text
Paper
Journal Article
Predictive representations: building blocks of intelligence
Carvalho, Wilka, Tomov, Momchil S, de Cothi, William, Caswell, Barry, Gershman, Samuel J
Published in arXiv.org (11.07.2024)
Get full text
Published in arXiv.org (11.07.2024)
Paper
Composing Task Knowledge with Modular Successor Feature Approximators
Carvalho, Wilka, Filos, Angelos, Lewis, Richard L, lee, Honglak, Singh, Satinder
Published in arXiv.org (28.01.2023)
Get full text
Published in arXiv.org (28.01.2023)
Paper
Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering
Chen, Bryant, Carvalho, Wilka, Baracaldo, Nathalie, Ludwig, Heiko, Edwards, Benjamin, Lee, Taesung, Molloy, Ian, Srivastava, Biplav
Year of Publication 08.11.2018
Year of Publication 08.11.2018
Get full text
Journal Article
Using gradients to detect backdoors in neural networks
Lee, Taesung, Carvalho, Wilka, Molloy, Ian M, Zhang, Jialong, Edwards, Benjamin J, Chen, Bryant
Year of Publication 28.09.2021
Get full text
Year of Publication 28.09.2021
Patent
Using gradients to detect backdoors in neural networks
Benjamin James Edwards, Bryant Chen, Ian Michael Molloy, Wilka Carvalho, Taesung Lee, Jialong Zhang
Year of Publication 13.01.2021
Get full text
Year of Publication 13.01.2021
Patent
Detecting poisoning attacks on neural networks by activation clustering
Lee, Taesung, Carvalho, Wilka, Zhang, Jialong, Molloy, Ian Michael, Edwards, Benjamin J, Ludwig, Heiko H, Chen, Bryant
Year of Publication 30.11.2021
Get full text
Year of Publication 30.11.2021
Patent
USING GRADIENTS TO DETECT BACKDOORS IN NEURAL NETWORKS
MOLLOY, Ian, ZHANG, Jialong, EDWARDS, Benjamin, LEE, Taesung, CARVALHO, Wilka, CHEN, Bryant
Year of Publication 24.10.2019
Get full text
Year of Publication 24.10.2019
Patent
Using Gradients to Detect Backdoors in Neural Networks
Lee, Taesung, Carvalho, Wilka, Molloy, Ian M, Zhang, Jialong, Edwards, Benjamin J, Chen, Bryant
Year of Publication 17.10.2019
Get full text
Year of Publication 17.10.2019
Patent
DETECTING POISONING ATTACKS ON NEURAL NETWORKS BY ACTIVATION CLUSTERING
Lee, Taesung, Carvalho, Wilka, Zhang, Jialong, Molloy, Ian Michael, Edwards, Benjamin J, Ludwig, Heiko H, Chen, Bryant
Year of Publication 13.02.2020
Get full text
Year of Publication 13.02.2020
Patent
Using gradients to detect backdoors in neural networks
LEE TAESUNG, MOLLOY IAN M, CARVALHO WILKA, EDWARDS BENJAMIN J, CHEN BRYANT, ZHANG JIALONG
Year of Publication 20.11.2020
Get full text
Year of Publication 20.11.2020
Patent