Obserwuj
Daniel Filan
Daniel Filan
PhD Student, UC Berkeley
Zweryfikowany adres z berkeley.edu - Strona główna
Tytuł
Cytowane przez
Cytowane przez
Rok
Self-modification of policy and utility function in rational agents
T Everitt, D Filan, M Daswani, M Hutter
Artificial General Intelligence: 9th International Conference, AGI 2016, New …, 2016
322016
Clusterability in neural networks
D Filan, S Casper, S Hod, C Wild, A Critch, S Russell
arXiv preprint arXiv:2103.03386, 2021
302021
Modeling agents with probabilistic programs
O Evans, A Stuhlmüller, J Salvatier, D Filan
URL: http://agentmodels. org, 2017
252017
Pruned Neural Networks are Surprisingly Modular
D Filan, S Hod, C Wild, A Critch, S Russell
arXiv preprint arXiv:2003.04881, 2020
192020
Graphical clusterability and local specialization in deep neural networks
S Casper, S Hod, D Filan, C Wild, A Critch, S Russell
ICLR 2022 Workshop on PAIR {\textasciicircum} 2Struct: Privacy …, 2022
92022
Quantifying local specialization in deep neural networks
S Hod, D Filan, S Casper, A Critch, S Russell
arXiv preprint arXiv:2110.08058, 2021
92021
Detecting modularity in deep neural networks
S Hod, S Casper, D Filan, C Wild, A Critch, S Russell
92021
Loss bounds and time complexity for speed priors
D Filan, J Leike, M Hutter
Artificial Intelligence and Statistics, 1394-1402, 2016
62016
Exploring hierarchy-aware inverse reinforcement learning
C Cundy, D Filan
arXiv preprint arXiv:1807.05037, 2018
42018
Importance and Coherence: Methods for Evaluating Modularity in Neural Networks
S Hod, S Casper, D Filan, C Wild, A Critch, S Russell
22020
Structure and Representation in Neural Networks
D Filan
2024
A nice representation of the Laplacian
D Filan
2022
Agents Using Speed Priors
D Filan
2015
What would it have looked like if it looked like I were in a superposition?
D Filan, JJ Hope
arXiv preprint arXiv:1509.04398, 2015
2015
Loss Bounds and Time Complexity for Speed Priors: Supplementary Material
D Filan, J Leike, M Hutter
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–15