Wenhao Hu

2692597H@student.gla.ac.uk

Research title: A New Point of View of Channel Pruning for Deep Neural Networks

Research Summary

Exploring optimization techniques for efficient TinyML

Exploring Novel Pruning Techniques for Deep Neural Networks and exploring the TinyML on further DNN architectures.

Publications

List by: Type | Date

Jump to: 2025 | 2024 | 2023
Number of items: 4.

2025

Hu, Wenhao, Henderson, Paul ORCID logoORCID: https://orcid.org/0000-0002-5198-7445 and Cano, Jose ORCID logoORCID: https://orcid.org/0000-0002-2243-389X (2025) ICE-Pruning: an Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks. In: International Joint Conference on Neural Networks (IJCNN 2025), Rome, Italy, 30 Jun - 05 Jul 2025, (Accepted for Publication)

2024

Hu, Wenhao, Henderson, Paul ORCID logoORCID: https://orcid.org/0000-0002-5198-7445 and Cano, Jose ORCID logoORCID: https://orcid.org/0000-0002-2243-389X (2024) DQA: An Efficient Method for Deep Quantization of Deep Neural Network Activations. In: NeurIPS 2024 Workshop Machine Learning with new Compute Paradigms, Vancouver, Canada, 14 December 2024,

Haris, Jude, Saha, Rappy ORCID logoORCID: https://orcid.org/0000-0001-9581-0193, Hu, Wenhao and Cano, José ORCID logoORCID: https://orcid.org/0000-0002-2243-389X (2024) Designing Efficient LLM Accelerators for Edge Devices. ARC-LG: New Approaches for Addressing the Computing Requirements of LLMs and GNNs, Buenos Aires, Argentina, 30 Jun 2024.

2023

Hu, Wenhao, Gibson, Perry ORCID logoORCID: https://orcid.org/0000-0003-3370-0698 and Cano, Jose ORCID logoORCID: https://orcid.org/0000-0002-2243-389X (2023) ICE-Pick: Iterative Cost-Efficient Pruning for DNNs. ICML 2023 Workshop on Neural Compression, Honolulu, Hawaii, USA, 28-29 July 2023.

This list was generated on Fri Jul 11 17:14:35 2025 BST.
Jump to: Conference or Workshop Item | Conference Proceedings
Number of items: 4.

Conference or Workshop Item

Haris, Jude, Saha, Rappy ORCID logoORCID: https://orcid.org/0000-0001-9581-0193, Hu, Wenhao and Cano, José ORCID logoORCID: https://orcid.org/0000-0002-2243-389X (2024) Designing Efficient LLM Accelerators for Edge Devices. ARC-LG: New Approaches for Addressing the Computing Requirements of LLMs and GNNs, Buenos Aires, Argentina, 30 Jun 2024.

Hu, Wenhao, Gibson, Perry ORCID logoORCID: https://orcid.org/0000-0003-3370-0698 and Cano, Jose ORCID logoORCID: https://orcid.org/0000-0002-2243-389X (2023) ICE-Pick: Iterative Cost-Efficient Pruning for DNNs. ICML 2023 Workshop on Neural Compression, Honolulu, Hawaii, USA, 28-29 July 2023.

Conference Proceedings

Hu, Wenhao, Henderson, Paul ORCID logoORCID: https://orcid.org/0000-0002-5198-7445 and Cano, Jose ORCID logoORCID: https://orcid.org/0000-0002-2243-389X (2025) ICE-Pruning: an Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks. In: International Joint Conference on Neural Networks (IJCNN 2025), Rome, Italy, 30 Jun - 05 Jul 2025, (Accepted for Publication)

Hu, Wenhao, Henderson, Paul ORCID logoORCID: https://orcid.org/0000-0002-5198-7445 and Cano, Jose ORCID logoORCID: https://orcid.org/0000-0002-2243-389X (2024) DQA: An Efficient Method for Deep Quantization of Deep Neural Network Activations. In: NeurIPS 2024 Workshop Machine Learning with new Compute Paradigms, Vancouver, Canada, 14 December 2024,

This list was generated on Fri Jul 11 17:14:35 2025 BST.

Supervisors