Phuoc Pham

Phuoc Pham


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 March 2021 in IEEE Access
Verified
Journal Article
Open access
PPPhuoc Pham
Phuoc Pham
JAJacob A. Abraham
Jacob A. Abraham
JCJaeyong Chung
Jaeyong Chung
Quantizing weights and activations of deep neural networks is essential for deploying them in resource-constrained devices, or cloud platforms for at-scale services. While binarization is a special case of quantization, this extreme case often leads to several training difficulties, and necessitates specialized models and training methods. As a result, recent quantization methods do not provide binarization, thus losing the most resource-efficient option, and quantized and binarized networks have been distinct research areas. We examine binarization difficulties in a quantization framework and find that all we need to enable the binary training are a symmetric quantizer, good initialization, and careful hyperparameter selection. These techniques also lead to substantial improvements in multi-bit quantization. We demonstrate our unified quantization framework, denoted as UniQ, on the ImageNet dataset with various architectures such as ResNet-18,-34 and MobileNetV2. For multi-bit quantization, UniQ outperforms existing methods to achieve the state-of-the-art accuracy. In binarization, the achieved accuracy is comparable to existing state-of-the-art methods even without modifying the original architectures.

10 October 2022
Verified
Conference Paper
Open access
PPPhuoc Pham
Phuoc Pham
VNVu Nguyen
Vu Nguyen
TNTien Nguyen
Tien Nguyen
Software testing is a process of evaluating and verifying whether a software product still works as expected, and it is repetitive, laborious, and time-consuming. To address this problem, automation tools have been developed to automate testing activities and enhance quality and delivery time. However, automation tools become less effective with continuous integration and continuous delivery (CI/CD) pipelines when the system under test is constantly changing. Recent advances in artificial intelligence and machine learning (AI/ML) present the potential for addressing important challenges in test automation. AI/ML can be applied to automate various testing activities such as detecting bugs and errors, maintaining existing test cases, or generating new test cases much faster than humans. In this study, we will outline testing activities where AI has significantly impacted and greatly enhanced the testing process. Based on that, we identify primary AI techniques that are used in each testing activity. Further, we conduct a comprehensive study of test automation tools to provide a clear look at the role of AI/ML technology in industrial testing tools. The results of this paper help researchers and practitioners understand the current state of AI/ML applied to software testing, which is the first important step towards achieving successful and efficient software testing.

8 April 2021 in Electronics
Verified
Journal Article
Open access
PDF file
PPPhuoc Pham
Phuoc Pham
JCJaeyong Chung
Jaeyong Chung
Network quantization becomes a crucial step when deploying deep models to the edge devices as it is hardware-friendly, offers memory and computational advantages, but it also suffers performance degradation as the result of limited representation capability. We address this issue by introducing conditional computing to low-bit quantized networks. Instead of using a fixed, single kernel for each layer, which usually does not generalize well across all input data, our proposed method tries to use multiple parallel kernels dynamically in conjunction with the winner-takes-all gating mechanism to select the best one to propagate information. Overall, our proposed method improves upon the prior work, without adding much computational overhead, results in better classification performance on the CIFAR-10 and CIFAR-100 datasets.

12 August 2025 in ACM Transactions on Design Automation of Electronic Systems
Verified
Journal Article
Open access
PPPhuoc Pham
Phuoc Pham
TPTae-Min Park
Tae-Min Park
SCSung-Hyuk Cho
Sung-Hyuk Cho
TMTayyeb Mahmood
Tayyeb Mahmood
JYJoon-Sung Yang
Joon-Sung Yang
JCJaeyong Chung
Jaeyong Chung
In electronic design automation (EDA), simulation models are often non-differentiable, and many design choices are discrete. As a result, greedy optimization methods based on numerical gradients are widely used, although they often lead to suboptimal solutions. In contrast, analytical methods may provide better solutions but require significant research effort. Reinforcement learning (RL) has been employed to address this problem; however, RL also suffers from notorious sample inefficiency, which is exaggerated in EDA because data sampling in EDA is very expensive due to slow simulations. This article proposes an alternative to RL for EDA, namely analytic gradient descent (AGD). Our method starts with a differentiable performance model, which can be either a learned surrogate or a static model. It then applies transformations similar to Shannon decomposition for each design variable in the performance model. Finally, one design option for each variable is selected using a one-hot variable, which is trained via a straight-through estimator (STE) through gradient descent. We demonstrate AGD on the well-known gate sizing problem using both a learned surrogate and a static model across 20 industrial benchmark circuits. Our experimental results show that the proposed method can outperform a several-decade-old commercial tool in the gate sizing task for 19 out of the 20 circuits.