Search Results for author: Reuben Feinman

Found 7 papers, 6 papers with code

Learning Task-General Representations with Generative Neuro-Symbolic Modeling

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.

Generating new concepts with hybrid neuro-symbolic models

no code implementations19 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.

A Linear Systems Theory of Normalizing Flows

1 code implementation15 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.

Learning a smooth kernel regularizer for convolutional neural networks

1 code implementation5 Mar 2019 Reuben Feinman, Brenden M. Lake

We propose a smooth kernel regularizer that encourages spatial correlations in convolution kernel weights.

L2 Regularization Object Recognition

Learning Inductive Biases with Simple Neural Networks

1 code implementation8 Feb 2018 Reuben Feinman, Brenden M. Lake

People use rich prior knowledge about the world in order to efficiently learn new concepts.

Object Recognition

Detecting Adversarial Samples from Artifacts

3 code implementations1 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.

Density Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.