Search Results for author: Chieh-Fang Teng

Found 11 papers, 1 papers with code

Compression-aware Projection with Greedy Dimension Reduction for Convolutional Neural Network Activations

no code implementations17 Oct 2021 Yu-Shan Tai, Chieh-Fang Teng, Cheng-Yang Chang, An-Yeu Wu

Our test results show that the proposed methods effectively reduce 2. 91x~5. 97x memory access with negligible accuracy drop on MobileNetV2/ResNet18/VGG16.

Dimensionality Reduction

Neural Network-Aided BCJR Algorithm for Joint Symbol Detection and Channel Decoding

no code implementations30 May 2020 Wen-Chiao Tsai, Chieh-Fang Teng, Han-Mo Ou, An-Yeu Wu

Recently, deep learning-assisted communication systems have achieved many eye-catching results and attracted more and more researchers in this emerging field.

Accumulated Polar Feature-based Deep Learning for Efficient and Lightweight Automatic Modulation Classification with Channel Compensation Mechanism

1 code implementation6 Jan 2020 Chieh-Fang Teng, Ching-Yao Chou, Chun-Hsiang Chen, An-Yeu Wu

Moreover, in applying this lightweight NN-CE in a time-varying fading channel, two efficient mechanisms of online retraining are proposed, which can reduce transmission overhead and retraining overhead by 90% and 76%, respectively.

General Classification

Syndrome-Enabled Unsupervised Learning for Neural Network-Based Polar Decoder and Jointly Optimized Blind Equalizer

no code implementations6 Jan 2020 Chieh-Fang Teng, Yen-Liang Chen

Recently, the syndrome loss has been proposed to achieve "unsupervised learning" for neural network-based BCH/LDPC decoders.

Low-Complexity LSTM-Assisted Bit-Flipping Algorithm for Successive Cancellation List Polar Decoder

no code implementations11 Dec 2019 Chun-Hsiang Chen, Chieh-Fang Teng, An-Yeu Wu

Polar codes have attracted much attention in the past decade due to their capacity-achieving performance.

Unsupervised Learning for Neural Network-based Polar Decoder via Syndrome Loss

no code implementations5 Nov 2019 Chieh-Fang Teng, An-Yeu Wu

To overcome such a constraint, syndrome loss has been proposed to penalize non-valid decoded codewords and achieve unsupervised learning for neural network-based decoder.

valid

Neural Network-based Equalizer by Utilizing Coding Gain in Advance

no code implementations11 Jul 2019 Chieh-Fang Teng, Han-Mo Ou, An-Yeu Wu

Recently, deep learning has been exploited in many fields with revolutionary breakthroughs.

Low-complexity Recurrent Neural Network-based Polar Decoder with Weight Quantization Mechanism

no code implementations29 Oct 2018 Chieh-Fang Teng, Chen-Hsi Wu, Kuan-Shiuan Ho, An-Yeu Wu

Polar codes have drawn much attention and been adopted in 5G New Radio (NR) due to their capacity-achieving performance.

Quantization

Polar Feature Based Deep Architectures for Automatic Modulation Classification Considering Channel Fading

no code implementations4 Oct 2018 Chieh-Fang Teng, Ching-Chun Liao, Chun-Hsiang Chen, An-Yeu Wu

Besides, the proposed CCN is also robust to channel fading, such as amplitude and phase offsets, and can improve the recognition accuracy by 14% under practical channel environments.

General Classification

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