Search Results for author: Dong-Hyun Lee

Found 7 papers, 3 papers with code

Discovery of Natural Language Concepts in Individual Units of CNNs

1 code implementation ICLR 2019 Seil Na, Yo Joong Choe, Dong-Hyun Lee, Gunhee Kim

Although deep convolutional networks have achieved improved performance in many natural language tasks, they have been treated as black boxes because they are difficult to interpret.

General Classification Translation

A Fast-Converged Acoustic Modeling for Korean Speech Recognition: A Preliminary Study on Time Delay Neural Network

no code implementations11 Jul 2018 Hosung Park, Dong-Hyun Lee, Minkyu Lim, Yoseb Kang, Juneseok Oh, Ji-Hwan Kim

In this paper, a time delay neural network (TDNN) based acoustic model is proposed to implement a fast-converged acoustic modeling for Korean speech recognition.

Speech Recognition

Cascading Denoising Auto-Encoder as a Deep Directed Generative Model

no code implementations23 Nov 2015 Dong-Hyun Lee

Recent work (Bengio et al., 2013) has shown howDenoising Auto-Encoders(DAE) become gener-ative models as a density estimator.


Towards Biologically Plausible Deep Learning

no code implementations14 Feb 2015 Yoshua Bengio, Dong-Hyun Lee, Jorg Bornschein, Thomas Mesnard, Zhouhan Lin

Neuroscientists have long criticised deep learning algorithms as incompatible with current knowledge of neurobiology.

Denoising Representation Learning

Difference Target Propagation

1 code implementation23 Dec 2014 Dong-Hyun Lee, Saizheng Zhang, Asja Fischer, Yoshua Bengio

Back-propagation has been the workhorse of recent successes of deep learning but it relies on infinitesimal effects (partial derivatives) in order to perform credit assignment.

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