no code implementations • 30 May 2023 • Yanli Zhou, Reuben Feinman, Brenden M. Lake
In few shot classification tasks, we find that people and the program induction model can make a range of meaningful compositional generalizations, with the model providing a strong account of the experimental data as well as interpretable parameters that reveal human assumptions about the factors invariant to category membership (here, to rotation and changing part attachment).
1 code implementation • ICLR 2021 • Reuben Feinman, Brenden M. Lake
We develop a generative neuro-symbolic (GNS) model of handwritten character concepts that uses the control flow of a probabilistic program, coupled with symbolic stroke primitives and a symbolic image renderer, to represent the causal and compositional processes by which characters are formed.
no code implementations • 19 Mar 2020 • Reuben Feinman, Brenden M. Lake
A second tradition has emphasized statistical knowledge, viewing conceptual knowledge as an emerging from the rich correlational structure captured by training neural networks and other statistical models.
1 code implementation • 15 Jul 2019 • Reuben Feinman, Nikhil Parthasarathy
Normalizing Flows are a promising new class of algorithms for unsupervised learning based on maximum likelihood optimization with change of variables.
1 code implementation • 5 Mar 2019 • Reuben Feinman, Brenden M. Lake
We propose a smooth kernel regularizer that encourages spatial correlations in convolution kernel weights.
1 code implementation • 8 Feb 2018 • Reuben Feinman, Brenden M. Lake
People use rich prior knowledge about the world in order to efficiently learn new concepts.
3 code implementations • 1 Mar 2017 • Reuben Feinman, Ryan R. Curtin, Saurabh Shintre, Andrew B. Gardner
Deep neural networks (DNNs) are powerful nonlinear architectures that are known to be robust to random perturbations of the input.
13 code implementations • 3 Oct 2016 • Nicolas Papernot, Fartash Faghri, Nicholas Carlini, Ian Goodfellow, Reuben Feinman, Alexey Kurakin, Cihang Xie, Yash Sharma, Tom Brown, Aurko Roy, Alexander Matyasko, Vahid Behzadan, Karen Hambardzumyan, Zhishuai Zhang, Yi-Lin Juang, Zhi Li, Ryan Sheatsley, Abhibhav Garg, Jonathan Uesato, Willi Gierke, Yinpeng Dong, David Berthelot, Paul Hendricks, Jonas Rauber, Rujun Long, Patrick McDaniel
An adversarial example library for constructing attacks, building defenses, and benchmarking both