6 citations · 13 across the 7 of their papers we have counts for
7 papers
Mapping-to-Parameter Nonlinear Functional Regression with Novel B-spline Free Knot Placement Algorithm
Chengdong Shi, Ching-Hsun Tseng, Wei Zhao +1
We propose a novel approach to nonlinear functional regression, called the Mapping-to-Parameter function model, which addresses complex and nonlinear functional regression problems…
EA-KD: Entropy-based Adaptive Knowledge Distillation
Chi-Ping Su, Ching-Hsun Tseng, Bin Pu +4
Knowledge distillation (KD) enables a smaller "student" model to mimic a larger "teacher" model by transferring knowledge from the teacher's output or features. However, most KD me…
A Novel Method of Fuzzy Topic Modeling based on Transformer Processing
Ching-Hsun Tseng, Shin-Jye Lee, Po-Wei Cheng +2
Topic modeling is admittedly a convenient way to monitor markets trend. Conventionally, Latent Dirichlet Allocation, LDA, is considered a must-do model to gain this type of informa…
Real-time Automatic M-mode Echocardiography Measurement with Panel Attention from Local-to-Global Pixels
Ching-Hsun Tseng, Shao-Ju Chien, Po-Shen Wang +4
Motion mode (M-mode) recording is an essential part of echocardiography to measure cardiac dimension and function. However, the current diagnosis cannot build an automatic scheme,…
EDU-level Extractive Summarization with Varying Summary Lengths
Yuping Wu, Ching-Hsun Tseng, Jiayu Shang +3
Extractive models usually formulate text summarization as extracting fixed top- salient sentences from the document as a summary. Few works exploited extracting finer-grained El…
Perturbated Gradients Updating within Unit Space for Deep Learning
Ching-Hsun. Tseng, Liu-Hsueh. Cheng, Shin-Jye. Lee +1
In deep learning, optimization plays a vital role. By focusing on image classification, this work investigates the pros and cons of the widely used optimizers, and proposes a new o…
UPANets: Learning from the Universal Pixel Attention Networks
Ching-Hsun Tseng, Shin-Jye Lee, Jia-Nan Feng +5
Among image classification, skip and densely-connection-based networks have dominated most leaderboards. Recently, from the successful development of multi-head attention in natura…