Lukasz Dudziak

Lukasz Dudziak

Auto-generated profile, based on publicly available information

Lukasz Dudziak

Samsung AI Center, Cambridge, Cambridgeshire, United Kingdom

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
13 November 2020
Verified
Book Chapter
Closed access
PDF file
RLRoyson Lee
Royson Lee
ŁDŁukasz Dudziak
Łukasz Dudziak
MAMohamed Abdelfattah
Mohamed Abdelfattah
SVStylianos I. Venieris
Stylianos I. Venieris
HKHyeji Kim
Hyeji Kim
NLNicholas D. Lane
Nicholas D. Lane

23 June 2024
Verified
Conference Paper
Open access
ZZZehuan Zhang
Zehuan Zhang
HFHongxiang Fan
Hongxiang Fan
HCHao (Mark) Chen
Hao (Mark) Chen
LDLukasz Dudziak
Lukasz Dudziak
WLWayne Luk
Wayne Luk
The increasing deployment of artificial intelligence (AI) for critical decision-making amplifies the necessity for trustworthy AI, where uncertainty estimation plays a pivotal role in ensuring trustworthiness. Dropout-based Bayesian Neural Networks (BayesNNs) are prominent in this field, offering reliable uncertainty estimates. Despite their effectiveness, existing dropout-based BayesNNs typically employ a uniform dropout design across different layers, leading to suboptimal performance. Moreover, as diverse applications require tailored dropout strategies for optimal performance, manually optimizing dropout configurations for various applications is both error-prone and labor-intensive. To address these challenges, this paper proposes a novel neural dropout search framework that automatically optimizes both the dropout-based BayesNNs and their hardware implementations on FPGA. We leverage one-shot supernet training with an evolutionary algorithm for efficient dropout optimization. A layer-wise dropout search space is introduced to enable the automatic design of dropout-based BayesNNs with heterogeneous dropout configurations. Extensive experiments demonstrate that our proposed framework can effectively find design configurations on the Pareto frontier. Compared to manually-designed dropout-based BayesNNs on GPU, our search approach produces FPGA designs that can achieve up to 33× higher energy efficiency. Compared to state-of-the-art FPGA designs of BayesNN, the solutions from our approach can achieve higher algorithmic performance and energy efficiency.