K
Kyunghyun Cho
Researcher at New York University
Publications - 351
Citations - 116609
Kyunghyun Cho is an academic researcher from New York University. The author has contributed to research in topics: Machine translation & Recurrent neural network. The author has an hindex of 77, co-authored 316 publications receiving 94919 citations. Previous affiliations of Kyunghyun Cho include Facebook & Université de Montréal.
Papers
More filters
Posted Content
Iterative Neural Autoregressive Distribution Estimator (NADE-k)
TL;DR: The proposed NADE-k is an unsupervised building block for deep learning that combines the desirable properties of NADE and multi-prediction training and uses an inference engine that is a superset of variational inference for Boltzmann machines.
Query-Efficient Imitation Learning for End-to-End Autonomous Driving
Jiakai Zhang,Kyunghyun Cho +1 more
TL;DR: SafeDAgger as discussed by the authors is an extension of the DAgger that is query-efficient and more suitable for end-to-end autonomous driving by iteratively collecting training examples from both reference and trained policies.
Proceedings ArticleDOI
On the Blind Spots of Model-Based Evaluation Metrics for Text Generation
TL;DR: This article explored a methodology for robustness analysis of text generation evaluation metrics: stress tests with synthetic data, and found that BERTScore is confused by truncation errors in summarization, and MAUVE (built on top of GPT-2) is insensitive to errors at the beginning or middle of generations.
Proceedings ArticleDOI
Gaussian-Bernoulli restricted Boltzmann machines and automatic feature extraction for noise robust missing data mask estimation
TL;DR: A missing data mask estimation method based on Gaussian-Bernoulli restricted Boltzmann machine (GRBM) trained on cross-correlation representation of the audio signal is presented in the study and is shown to provide a performance improvement in the speech recognition accuracy over the previous multifeature approaches.