Hao-Wei Chiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hao-Wei Chiang has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- An-Yeu Wu
Graduate Institute of Electronics Engineering, National Taiwan University, Taipei, Taiwan
2 shared publications - Cheng-Lin Hsieh
Computer Science and Engineering Department, University of Michigan, Ann Arbor, MI, USA
1 shared publication - Chi-Tse Huang
Graduate Institute of Electronics Engineering, National Taiwan University, Taipei, Taiwan
1 shared publication - Hsiang-Yun Cheng
Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan
1 shared publication - Ming-Hsiu Lee
Macronix Emerging Central Laboratory, Macronix International Company Ltd., Hsinchu, Taiwan
1 shared publication - Po-Hao Tseng
Macronix International Co., Ltd., Hsinchu, Taiwan
1 shared publication
Latest Publications
- Open Access
- 20 January 2025
- Published by Association for Computing Machinery (ACM)
- p. 93-99
Efficient and Reliable Vector Similarity Search Using Asymmetric Encoding with NAND-Flash for Many-Class Few-Shot Learning
While memory-augmented neural networks (MANNs) offer an effective solution for few-shot learning (FSL) by integrating deep neural networks with external memory, the capacity requirements and energy overhead of data movement become enormous due to the large number of support vectors in many-class FSL scenarios. Various in-memory search solutions have emerged to improve the energy efficiency of MANNs. NAND-based multi-bit content addressable memory (MCAM) is a promising option due to its high density and large capacity. Despite its potential, MCAM faces limitations such as a restricted number of word lines, limited quantization levels, and non-ideal effects like varying string currents and bottleneck effects, which lead to significant accuracy drops. To address these issues, we propose several innovative methods. First, the Multi-bit Thermometer Code (MTMC) leverages the extensive capacity of MCAM to enhance vector precision using cumulative encoding rules, thereby mitigating the bottleneck effect. Second, the Asymmetric Vector Similarity Search (AVSS) reduces the precision of the query vector while maintaining that of the support vectors, thereby minimizing the search iterations and improving efficiency in many-class scenarios. Finally, the Hardware-Aware Training (HAT) method optimizes controller training by modeling the hardware characteristics of MCAM, thus enhancing the reliability of the system. Our integrated framework reduces search iterations by up to 32×, and increases overall accuracy by 1.58% to 6.94%.
- 20 January 2025
- Published by Association for Computing Machinery (ACM)
- p. 93-99
Open AccessEfficient and Reliable Vector Similarity Search Using Asymmetric Encoding with NAND-Flash for Many-Class Few-Shot Learning
While memory-augmented neural networks (MANNs) offer an effective solution for few-shot learning (FSL) by integrating deep neural networks with external memory, the capacity requirements and energy overhead of data movement become enormous due to the large number of support vectors in many-class FSL scenarios. Various in-memory search solutions have emerged to improve the energy efficiency of MANNs. NAND-based multi-bit content addressable memory (MCAM) is a promising option due to its high density and large capacity. Despite its potential, MCAM faces limitations such as a restricted number of word lines, limited quantization levels, and non-ideal effects like varying string currents and bottleneck effects, which lead to significant accuracy drops. To address these issues, we propose several innovative methods. First, the Multi-bit Thermometer Code (MTMC) leverages the extensive capacity of MCAM to enhance vector precision using cumulative encoding rules, thereby mitigating the bottleneck effect. Second, the Asymmetric Vector Similarity Search (AVSS) reduces the precision of the query vector while maintaining that of the support vectors, thereby minimizing the search iterations and improving efficiency in many-class scenarios. Finally, the Hardware-Aware Training (HAT) method optimizes controller training by modeling the hardware characteristics of MCAM, thus enhancing the reliability of the system. Our integrated framework reduces search iterations by up to 32×, and increases overall accuracy by 1.58% to 6.94%.
- 9 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (8) , 11081-11095
EECS: Efficient End-Cloud Collaborative System With On-Demand Offloading Mechanism for Convolutional Neural Network
The end-cloud synergy with neural networks offers significant promise for enhancing AI-IoT systems. Numerous studies have been conducted to effectively address the dynamic and resource-constrained nature of IoT; however, challenges persist in adaptability to constraints, horizontal integration between technologies, and system-level optimization. In this paper, we propose an end-cloud collaborative system (EECS) with an on-demand offloading mechanism for AI-IoT. We enhance three critical areas previously narrowly explored: model pruning to fit into the end device’s constraints, dynamic data transmission between end and cloud, and an effective offloading policy. We pay particular attention to the constraints imposed by multiply-and-add (MAC) operations and bandwidth (BW) at the end, with a focus on image classification tasks. Our contributions are threefold. First, we introduce a two-stage trainable pruning method that can automatically adjust the end model to end constraints and optimize from a system-wide perspective. Second, we propose an adaptive mechanism that accommodates fluctuating bandwidth conditions based on our trainable pruning, integrating static pruning with dynamic inference. Third, we develop a smart offloading policy that enhances decision-making, thereby elevating system-level efficiency. Finally, our EECS shows substantial improvements, achieving 2.6×~4× reductions in MAC costs and 3.8×~10.4× reductions in BW costs compared to existing approaches, based on evaluations using the CIFAR-100 and Tiny-ImageNet-200 datasets.
- 9 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (8) , 11081-11095
EECS: Efficient End-Cloud Collaborative System With On-Demand Offloading Mechanism for Convolutional Neural Network
The end-cloud synergy with neural networks offers significant promise for enhancing AI-IoT systems. Numerous studies have been conducted to effectively address the dynamic and resource-constrained nature of IoT; however, challenges persist in adaptability to constraints, horizontal integration between technologies, and system-level optimization. In this paper, we propose an end-cloud collaborative system (EECS) with an on-demand offloading mechanism for AI-IoT. We enhance three critical areas previously narrowly explored: model pruning to fit into the end device’s constraints, dynamic data transmission between end and cloud, and an effective offloading policy. We pay particular attention to the constraints imposed by multiply-and-add (MAC) operations and bandwidth (BW) at the end, with a focus on image classification tasks. Our contributions are threefold. First, we introduce a two-stage trainable pruning method that can automatically adjust the end model to end constraints and optimize from a system-wide perspective. Second, we propose an adaptive mechanism that accommodates fluctuating bandwidth conditions based on our trainable pruning, integrating static pruning with dynamic inference. Third, we develop a smart offloading policy that enhances decision-making, thereby elevating system-level efficiency. Finally, our EECS shows substantial improvements, achieving 2.6×~4× reductions in MAC costs and 3.8×~10.4× reductions in BW costs compared to existing approaches, based on evaluations using the CIFAR-100 and Tiny-ImageNet-200 datasets.