HTC

∙ Taoyuan , Taiwan, Province of China ∙ 0 followers

HTC Corporation is a Taiwanese consumer electronics company headquartered in Xindian District, New Taipei City, Taiwan.

Distributed Training Large-Scale Deep Architectures

Scale of data and scale of computation infrastructures together enable t...
08/10/2017 ∙ by Shang-Xuan Zou, et al. ∙ 0 ∙ share

read it
Representation Learning on Large and Small Data

Deep learning owes its success to three key factors: scale of data, enha...
07/25/2017 ∙ by Chun-Nan Chou, et al. ∙ 0 ∙ share

read it
BDA-PCH: Block-Diagonal Approximation of Positive-Curvature Hessian for Training Neural Networks

We propose a block-diagonal approximation of the positive-curvature Hess...
02/19/2018 ∙ by Sheng-Wei Chen, et al. ∙ 0 ∙ share

read it
Backward Reduction of CNN Models with Information Flow Analysis

This paper proposes backward reduction, an algorithm that explores the c...
07/16/2018 ∙ by Yu-Hsun Lin, et al. ∙ 0 ∙ share

read it
MBS: Macroblock Scaling for CNN Model Reduction

We estimate the proper channel (width) scaling of Convolution Neural Net...
09/18/2018 ∙ by Yu-Hsun Lin, et al. ∙ 0 ∙ share

read it
Distributed Layer-Partitioned Training for Privacy-Preserved Deep Learning

Deep Learning techniques have achieved remarkable results in many domain...
04/12/2019 ∙ by Chun-Hsien Yu, et al. ∙ 0 ∙ share

read it
KG-GAN: Knowledge-Guided Generative Adversarial Networks

Generative adversarial networks (GANs) learn to mimic training data that...
05/29/2019 ∙ by Che-Han Chang, et al. ∙ 0 ∙ share

read it
Hypernetwork-Based Augmentation

Data augmentation is an effective technique to improve the generalizatio...
06/11/2020 ∙ by Chih-Yang Chen, et al. ∙ 0 ∙ share

read it

HTC

Featured Researchers

Edward Y. Chang

Chun-Nan Chou

Che-Han Chang

Ting-Wei Lin

Edward Chang

Chia-Chin Tsao

Kuan-Chieh Tung

Cheng-Lung Sung

Chuen-Kai Shie

Jocelyn Chang

Szu-Ying Chen

Distributed Training Large-Scale Deep Architectures

Representation Learning on Large and Small Data

BDA-PCH: Block-Diagonal Approximation of Positive-Curvature Hessian for Training Neural Networks

Backward Reduction of CNN Models with Information Flow Analysis

MBS: Macroblock Scaling for CNN Model Reduction

Distributed Layer-Partitioned Training for Privacy-Preserved Deep Learning

KG-GAN: Knowledge-Guided Generative Adversarial Networks

Hypernetwork-Based Augmentation