Now 12454 visitors
Today:0 Yesterday:0
Total: 160068
216S 51P 5R
2026-10-21, Week 43
Member Login
TACT Journal Homepage
Call for Paper
Committee
Find My Paper
Author Homepage
Statistics & History
Welcome Message
Paper Procedure
FAQ
Paper Archives
Outstanding Papers
Author Homepage
- Paper Procedure
- Journal Procedure
- Presentation Tips
Program & Proceedings
Program with Papers
Plenary Session
Tutorial Session
Presentation Platform
Hotel & Travel Info
About Korea
Accommodation
Transportation
VISA
Other Infomation
Photo Gallery
Scheduler Login
Seminar
Archives Login
Sponsors
Presentation Assistant
Go to [Q&A Session]
Paper Number
Paper Title
Keyword
ICACT20240009 Slide.00
[Big Slide]
Chrome
Click!!
I am Francis Lau, the presenter of this paper
ICACT20240009 Slide.01
[Big Slide]
Chrome
Click!!
These are the contents of the presentation
ICACT20240009 Slide.02
[Big Slide]
Chrome
Click!!
Deep learning has been applied in our daily lives. Examples are object classification, object detection and language translation
ICACT20240009 Slide.03
[Big Slide]
Chrome
Click!!
The goal of deep learning is to learn from data
ICACT20240009 Slide.04
[Big Slide]
Chrome
Click!!
Characteristics of deep learning model include the following
ICACT20240009 Slide.05
[Big Slide]
Chrome
Click!!
The communication model is similar
ICACT20240009 Slide.06
[Big Slide]
Chrome
Click!!
Recurrent neural network (RNN) takes the previous output and hidden states as inputs so that the composite input at time 𝑡 has some historical information about what happens at time T<𝑡
ICACT20240009 Slide.07
[Big Slide]
Chrome
Click!!
Convolutional code
ICACT20240009 Slide.08
[Big Slide]
Chrome
Click!!
Decoding convolutional code via bi-directional RNN network
ICACT20240009 Slide.09
[Big Slide]
Chrome
Click!!
Convolutional Hadamard code
ICACT20240009 Slide.10
[Big Slide]
Chrome
Click!!
Turbo Hadamard code
ICACT20240009 Slide.11
[Big Slide]
Chrome
Click!!
Conventional CHC and THC decoders
ICACT20240009 Slide.12
[Big Slide]
Chrome
Click!!
CHC decoder based on bi-directional LSTM
ICACT20240009 Slide.13
[Big Slide]
Chrome
Click!!
End-to-end THC decoder based on bi-directional LSTM
ICACT20240009 Slide.14
[Big Slide]
Chrome
Click!!
Training LSTM-CHC decoder
ICACT20240009 Slide.15
[Big Slide]
Chrome
Click!!
Training evolution
ICACT20240009 Slide.16
[Big Slide]
Chrome
Click!!
Performance of proposed LSTM-CHC decoder
ICACT20240009 Slide.17
[Big Slide]
Chrome
Click!!
Training LSTM-THC decoder
ICACT20240009 Slide.18
[Big Slide]
Chrome
Click!!
Performance of proposed LSTM-THC decoder
ICACT20240009 Slide.19
[Big Slide]
Chrome
Click!!
Future works
ICACT20240009 Slide.20
[Big Slide]
Chrome
Click!!
Q&A