Search Results for author: Eric Wang

Found 9 papers, 3 papers with code

The Dynamic Sensorium competition for predicting large-scale mouse visual cortex activity from videos

1 code implementation31 May 2023 Polina Turishcheva, Paul G. Fahey, Laura Hansel, Rachel Froebe, Kayla Ponder, Michaela Vystrčilová, Konstantin F. Willeke, Mohammad Bashiri, Eric Wang, Zhiwei Ding, Andreas S. Tolias, Fabian H. Sinz, Alexander S. Ecker

We hope this competition will continue to strengthen the accompanying Sensorium benchmarks collection as a standard tool to measure progress in large-scale neural system identification models of the entire mouse visual hierarchy and beyond.

Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve

no code implementations7 Dec 2022 Juhan Bae, Michael R. Zhang, Michael Ruan, Eric Wang, So Hasegawa, Jimmy Ba, Roger Grosse

Variational autoencoders (VAEs) are powerful tools for learning latent representations of data used in a wide range of applications.

Neuro-Symbolic Entropy Regularization

no code implementations25 Jan 2022 Kareem Ahmed, Eric Wang, Kai-Wei Chang, Guy Van Den Broeck

We propose a loss, neuro-symbolic entropy regularization, that encourages the model to confidently predict a valid object.

Structured Prediction valid

Probabilistic Sufficient Explanations

1 code implementation21 May 2021 Eric Wang, Pasha Khosravi, Guy Van Den Broeck

Understanding the behavior of learned classifiers is an important task, and various black-box explanations, logical reasoning approaches, and model-specific methods have been proposed.

Logical Reasoning

Generalization in data-driven models of primary visual cortex

no code implementations ICLR 2021 Konstantin-Klemens Lurz, Mohammad Bashiri, Konstantin Willeke, Akshay Jagadish, Eric Wang, Edgar Y. Walker, Santiago A Cadena, Taliah Muhammad, Erick Cobos, Andreas S. Tolias, Alexander S Ecker, Fabian H. Sinz

With this new readout we train our network on neural responses from mouse primary visual cortex (V1) and obtain a gain in performance of 7% compared to the previous state-of-the-art network.

Transfer Learning

Joint Analysis of Time-Evolving Binary Matrices and Associated Documents

no code implementations NeurIPS 2010 Eric Wang, Dehong Liu, Jorge Silva, Lawrence Carin, David B. Dunson

An objective of such analysis is to infer structure and inter-relationships underlying the matrices, here defined by latent features associated with each axis of the matrix.

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