K
Kilian Q. Weinberger
Researcher at Cornell University
Publications - 241
Citations - 71535
Kilian Q. Weinberger is an academic researcher from Cornell University. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 76, co-authored 222 publications receiving 49707 citations. Previous affiliations of Kilian Q. Weinberger include University of Washington & Washington University in St. Louis.
Papers
More filters
Posted Content
Densely Connected Convolutional Networks
TL;DR: The Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion, and has several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.
Posted Content
Deep Networks with Stochastic Depth
TL;DR: Stochastic depth as discussed by the authors randomly drops a subset of layers during training and bypasses them with the identity function, which can increase the depth of residual networks even beyond 1200 layers and still yield meaningful improvements in test error.
Proceedings ArticleDOI
Feature hashing for large scale multitask learning
TL;DR: In this article, the authors provide exponential tail bounds for feature hashing and show that the interaction between random subspaces is negligible with high probability, and demonstrate the feasibility of this approach with experimental results for a new use case.
Proceedings Article
BERTScore: Evaluating Text Generation with BERT
TL;DR: This article proposed BERTScore, an automatic evaluation metric for text generation, which computes a similarity score for each token in the candidate sentence with each token from the reference sentence. But instead of exact matches, they compute token similarity using contextual embeddings.
Posted Content
Marginalized Denoising Autoencoders for Domain Adaptation
TL;DR: This paper proposed marginalized SDA (mSDA) that addresses two crucial limitations of stacked denoising autoencoders: high computational cost and lack of scalability to high-dimensional features.