80 citations
- R. Salakhutdinov6 · h 120
- Ryan M. Rogers3 · h 19
- Ahmed Hassan Awadallah2 profiles2 · h 38
- Alexandros Kalousis2 profiles2 · h 34
- Devendra Singh Chaplot2 · h 24
- Jason Ramapuram2 profiles2 · h 12
- J. Susskind2 · h 35
- Marco Gaboardi2 · h 33
- Russ Webb2 · h 7
- Shuangfei Zhai2 · h 28
- S. Longpre2 · h 21
- Zhucheng Tu2 · h 8
- Carnegie Mellon UniversityUS10 papers
- Google (United States)US5 papers
- Apple (United States)US4 papers
- Stanford UniversityUS4 papers
- University of WashingtonUS3 papers
- Binghamton UniversityUS2 papers
- Microsoft (United States)US2 papers
- University at Buffalo, State University of New YorkUS2 papers
- University of GenevaCH2 papers
- University of TorontoCA2 papers
- Allen InstituteUS1 paper
- Amsterdam University of the ArtsNL1 paper
8 papers · 1 filter
MultiBench: Multiscale Benchmarks for Multimodal Representation Learning
Paul Pu Liang, Yiwei Lyu, Xiang Fan +9
Learning multimodal representations involves integrating information from multiple heterogeneous sources of data. It is a challenging yet crucial area with numerous real-world appl…
Collegial Ensembles
Etai Littwin, Ben Myara, Sima Sabah +3
Modern neural network performance typically improves as model size increases. A recent line of research on the Neural Tangent Kernel (NTK) of over-parameterized networks indicates…
Understanding and Mitigating Exploding Inverses in Invertible Neural Networks
Jens Behrmann, Paul Vicol, Kuan-Chieh Wang +2
Invertible neural networks (INNs) have been used to design generative models, implement memory-saving gradient computation, and solve inverse problems. In this work, we show that c…
Capsules with Inverted Dot-Product Attention Routing
Yao-Hung Hubert Tsai, Nitish Srivastava, Hanlin Goh +1
We introduce a new routing algorithm for capsule networks, in which a child capsule is routed to a parent based only on agreement between the parent's state and the child's vote. T…
Neural Rule Ensembles: Encoding Sparse Feature Interactions into Neural Networks
Gitesh Dawer, Yangzi Guo, Sida Liu +1
Artificial Neural Networks form the basis of very powerful learning methods. It has been observed that a naive application of fully connected neural networks to data with many irre…
Adversarial Fisher Vectors for Unsupervised Representation Learning
Shuangfei Zhai, Walter Talbott, Carlos Guestrin +1
We examine Generative Adversarial Networks (GANs) through the lens of deep Energy Based Models (EBMs), with the goal of exploiting the density model that follows from this formulat…