R
Ruslan Salakhutdinov
Researcher at Carnegie Mellon University
Publications - 457
Citations - 142495
Ruslan Salakhutdinov is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 107, co-authored 410 publications receiving 115921 citations. Previous affiliations of Ruslan Salakhutdinov include Carnegie Learning & University of Toronto.
Papers
More filters
Proceedings Article
Learning Wake-Sleep recurrent attention models
TL;DR: In this article, a Wake-Sleep Recurrent Attention Model (WRSAM) is proposed to speed up the training of stochastic attention networks in the domains of image classification and caption generation.
Proceedings ArticleDOI
Complex Transformer: A Framework for Modeling Complex-Valued Sequence
TL;DR: A Complex Transformer is proposed, which incorporates the transformer model as a backbone for sequence modeling; the model achieves state-of-the-art performance on the MusicNet dataset and an In-phase Quadrature signal dataset.
Proceedings ArticleDOI
Embodied Multimodal Multitask Learning
TL;DR: This paper proposes a multitask model which facilitates knowledge transfer across tasks by disentangling the knowledge of words and visual attributes in the intermediate representations and shows that this disentanglement of representations makes the model modular and interpretable which allows for transfer to instructions containing new concepts.
Proceedings Article
Knowledge-based Word Sense Disambiguation using Topic Models.
TL;DR: The proposed method is a variant of Latent Dirichlet Allocation in which the topic proportions for a document are replaced by synset proportions and it outperforms the state-of-the-art unsupervised knowledge-based WSD system by a significant margin.
Posted Content
Style Transfer Through Back-Translation
TL;DR: This article used adversarial generation techniques to make the output match the desired style, which showed improvements both in automatic evaluation of style transfer and in manual evaluation of meaning preservation and fluency.