中央研究院 資訊科學研究所

活動訊息

友善列印

列印可使用瀏覽器提供的(Ctrl+P)功能

TIGP (SNHCC) --An Introduction of Quantum Circuit Learning and Its Applications on Speech and Language Processing

:::

TIGP (SNHCC) --An Introduction of Quantum Circuit Learning and Its Applications on Speech and Language Processing

  • 講者Huck C.-H. Yang 先生 (Georgia Institute of Technology (USA))
    邀請人:TIGP (SNHCC)
  • 時間2022-03-07 (Mon.) 14:00 – 16:00
  • 地點中研院資訊所,新館106會議室
摘要

 

 Variational Quantum Circuit (VQC) based algorithms have recently attracted great attention due to their potential applications on commercially available noisy intermediate-scale quantum (NISQ) computing devices (5 to 200 qubits). Meanwhile, both theoretical justification and empirical investigations of hybrid VQC and machine learning models are still relatively limited for NISQ based quantum computers. This talk will introduce some basic background and future directions on designing VQC models with deep representation learning algorithms with empirical applications for speech recognition [1] and text classification [2].

BIO

Chao-Han Huck Yang is a fifth-year Ph.D. candidate at Georgia Institute of Technology, Atlanta, USA. His research interests focus on characterizing the reliability and robustness of machine learning models toward speech, acoustic, and time-series data processing. He received NeurIPS outstanding reviewer award in 2021, Xanadu AI Global Quantum ML Competition First Prize in 2019, Wallace H. Coulter Fellowship in 2017, and travel grants from ICML, AAAI, and ICASSP. (https://scholar.google.com/citations?hl&user=TT3XJW8AAAAJ)

 

Related Reference:

 

1.     "Decentralizing feature extraction with quantum convolutional neural network for automatic speech recognition." Yang, CHH, et al. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2021.

 

2.     “When BERT Meets Quantum Temporal Convolution Learning for Text Classification in Heterogeneous Computing.“ Yang, CHH, et al. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2022.

 

3.     “QTN-VQC: An End-to-End Learning framework for Quantum Neural Networks.” Qi, J et al. NeurIPS 2021 Workshop on Quantum Tensor Networks in Machine Learning