Xinhua Zhang

An Introduction to Graph Neural Network (GNN) and Its Applications in Drug Response Prediction by Dennis Wang is one of the workshops for #apbjc. Read more about the workshop and other at: https://buff.ly/4bsttvm

6

Current quantum computers belong to the noisy intermediate-scale quantum class, characterized by noisy qubits, limited qubit capabilities, and limited circuit depth. These limitations have led to the development of hybrid quantum- classical algorithms that split the computational cost between classical and quantum hardware. Among the hybrid algorithms, the variational quantum eigensolver (VQE) is mentioned. The VQE is a variational quantum algorithm designed to estimate the eigenvalues and eigenvectors of a system on universal-gate quantum architectures. A canonical problem in electromagnetics is the computation of eigenmodes within waveguides. Following the finite difference method, the wave equation can be recast as an eigenvalue problem. This work exploits the quantum super- position and entanglement in quantum computing to solve the square waveguide mode problem. This algorithm is expected to demonstrate exponentially efficiency over classical computational techniques as the qubit count increases. The simulations were performed on IBM’s 3-qubit quantum simulator, Qasm IBM Simulator. A shot-based simulation was performed considering computationally based measurements of the quantum hardware. The results of the probabilistic read-out, reported in terms of 2D eigenmode field distributions, are close to ideal values with a few number of qubits, confirming the possibility to exploit the quantum advantage to formulate innovative eigensolvers. Check this out!

10

Witness a landmark moment in AI: Dr Yang Liu (HKBU Department of Computer Science) originated a pioneering polarised message-passing (PMP) framework, featured in the prestigious journal of 𝘈𝘳𝘵𝘪𝘧𝘪𝘤𝘪𝘢𝘭 𝘐𝘯𝘵𝘦𝘭𝘭𝘪𝘨𝘦𝘯𝘤𝘦. Dr Liu debuted three innovative PMP-augmented graph neural networks (GNNs), surpassing leading methodologies in diverse real-world applications, and forging new industry benchmarks with unparalleled precision and efficiency. 𝐑𝐞𝐚𝐝 𝐭𝐡𝐞 𝐏𝐚𝐩𝐞𝐫: https://lnkd.in/gTKpBqpc      🗝 Cluster: Data Analytics and Artificial Intelligence #Cluster_Data_Analytics_and_Artificial_Intelligence #HKBU #ResearchOffice #HKBUResearch #HKBURO #HKBUCOMP #ComputerScience #PolarizedMessagePassing #GraphNeuralNetwork #GNN #AIJ #ArtificialIntelligence #AI #Elsevier Elsevier

18

Excited to share my latest research as the first author on leveraging transformer-based language models to study clinicians' cognitive effort while using the electronic health records (EHRs). Title: Measuring Cognitive Effort Using Tabular Transformer-Based Language Models of Electronic Health Record-Based Audit Log Action Sequences In this paper, we explore the innovative use of tabular transformer-based models to measure clinicians’ cognitive effort in completing clinical tasks on the EHR, which we term ‘action entropy.’ We trained our models exclusively on granular user interaction logs from the EHR (i.e., audit logs or access logs). Once further validated, our metric may pave the way for improved understanding of various work pattern phenotypes and how they relate to increased burden and clinical outcomes in healthcare settings. A huge thank you to my co-authors and collaborators for their invaluable contributions and support. This work wouldn’t have been possible without our collective effort and dedication. 🙏 I’m incredibly proud of this accomplishment and excited about the potential impact our research can have on the healthcare industry. Feel free to reach out if you have any questions or are interested in discussing our findings! #Research #Healthcare #EHR #Transformers #LanguageModels #MachineLearning #DataScience #BiomedicalInformatics

19

Nonlinear controller for SEPIC with single variable to tune Youssef El Haj, Vijay Sood*, Ahmed Sheir, Ruth Milman Abstract: This work proposes a systematic approach to design a novel integral sliding mode controller (ISMC) for a single-ended primary-inductor converter (SEPIC) with only one tunable parameter where the upper and the lower bounds are derived. The designed surface results in a minimal chattering behaviour at the output voltage as well as at the duty cycle and allows for operating the SEPIC at a fixed switching frequency. The proposed controller can withstand up to a 70% variation in the input voltage and 100% variation on the load side in addition to superior performance for a cold start. The proposed controller and the corresponding mathematical formulation were simulated in a Simulink environment and experimentally tested via a scaled prototype. The proposed controller performance is also compared to a Type-II and integral Linear-Quadratic Regulators (LQR). https://lnkd.in/gNQD9ie3

35

Glad to see #AI helps advancing noninvasive #BCI. This paper published at PNAS Nexus, a journal by the National Academy of Science, reports unmatched performance for AI-enabled #brain-computer interface to continuously tracking a virtual object, in humans using noninvasive #EEG only. Also published is 150-hours continuous #EEG-BCI #data in 28 #human participants. A great job by Dylan Forenzo, a Sr. #BME PhD student at #CMU, and Hao Zhu, a former MS BME student at CMU. Brain intention recruits a group of neurons which activation propagates to the scalp, being small but picked up by EEG. AI helps extracting extremely small neural signals from scalp EEG and turn them into control command to control a computer. Thanks to National Center for Complementary and Integrative Health, National Institute of Neurological Disorders and Stroke (NINDS), and National Institute of Biomedical Imaging and Bioengineering (NIBIB) for funding support, which made this work possible. #neuroengineering #neurotechnology #neuroscience #BIomedicalEngineering #Bioengineering #BMI #BCI #electroencephalography #DL #ML #signalprocessing

117

7 Comments

I am thrilled to share our latest preprint accepted at the 61st Design Automation Conference (DAC): "Deep Reinforcement Learning based Online Scheduling Policy for Deep Neural Network Multi-Tenant Multi-Accelerator Systems". The paper discusses the increasing use of cloud services for executing Deep Neural Networks (DNNs) and the challenges faced by service providers in managing multitenancy while meeting execution time constraints and cost-effectiveness. We introduce RELMAS, a deep reinforcement learning algorithm for online scheduling of DNNs in multi-tenant environments. RELMAS considers dataflow heterogeneity and memory bandwidth contention of accelerators to optimize Service-Level-Agreement (SLA) satisfaction rates and hardware utilization. When we applied RELMAS to a heterogeneous multi-accelerator system, we observed a 173% improvement in SLA satisfaction rate compared to state-of-the-art scheduling techniques across various workload scenarios, with less than a 1.5% energy overhead. Preprint: https://lnkd.in/e84tMNFX Francesco Giulio Blanco, Enrico Russo, Davide Patti, Giuseppe Ascia #HardwareAcceletarors #RealtimeScheduling #MultiTenant #MultiAcceleratorSystems #ReinforcementLearning #ServiceLevelAgreement #DAC #DAC61

83

3 Comments

✨ Jiayuan Hao is a second-year PhD student in biostatistics program. Hao’s area of interest is environmental statistics and environmental health. “I would like to be a researcher in biostatistics developing advanced statistical tools for complicated environmental health studies after graduation,” shares Hao. 🖥️ This award enabled Hao to train in Deep Learning models more efficiently. Similarly, accessing APIs from OpenAI broadened Hao's perspective on the application of AI techniques in health-related research. 💡 “Last year, I stepped out of my comfort zone and began genomics research. Although, I initially found it incredibly challenging, my persistence in seeking out resources and mentors helped me overcome the steep learning curve. It shattered my self-imposed limitations and instilled in me a newfound confidence. The key takeaway was a reaffirmation of my belief: with dedication and perseverance, I can excel in any field of my choosing.” 💭 Hao encourages other students to consider applying for the Student Success Award. "It represents an excellent chance to reflect on the challenges they have overcome in the past year and to set new objectives for the future. This process is not just about recognition but also about personal growth and envisioning a path forward."

10

We have a new article just published in Neural Computing and Application (Springer Nature) on #DIGITALTWIN for #PREDICTIVEMAINTENANCE. https://lnkd.in/gg_28cRx

22

1 Comment

We invite research submissions on Quantum Computing and Reinforcement Learning (QCRL) at IEEE Quantum Week 2024 (Montreal, Sep. 15-20, 2024). https://2024.qcrl.io/ Scope and Topics: Topics relevant to this session include, but are not limited to: - Theoretical studies of quantum reinforcement learning algorithms - Challenges in quantum reinforcement learning in the NISQ era - Quantum reinforcement learning under the influence of quantum device noise QRL in the context of trustworthy ML (e.g., adversarial attacks, federated learning) - Quantum reinforcement learning for scientific discovery, commercial, and industrial applications - Benchmarking QRL algorithms - Reinforcement learning for quantum control, quantum error correction, and quantum error mitigation - Reinforcement learning for quantum architecture search, optimization, and program synthesis - Hybrid RL-QC systems design Important Deadlines: - Jul 10, 2024: Abstract Due Date - Jul 15, 2024: Paper Submission Due Date - Jul 28, 2024: Notification of Paper Acceptance - Aug 5, 2024: Camera-ready Papers Due #quantum #machinelearning #reinforcementlearning

30

Joint work with Aby Philip, Soorya Rethinasamy, and Vincent Russo now published in Quantum - the open journal for quantum science: https://lnkd.in/giwDBREV Title: Schrödinger as a Quantum Programmer: Estimating Entanglement via Steering Popular Summary: Entanglement is a unique feature of quantum mechanics, initially brought to light by Einstein, Podolsky, and Rosen. Determining whether a general quantum state is entangled or not, known as the separability problem, is of fundamental interest and relevant to various fields of physics: condensed matter, quantum gravity, quantum optics, and quantum information science. Motivated by the rapid development of quantum computers, we provide a variational quantum steering algorithm (VQSA) to address the separability problem. The quantum steering effect, discovered by Schrödinger, is central to the design of our algorithm, which is implementable on quantum computers that are available today. We provide benchmarks and simulations of our algorithm and establish a meaningful connection between steering, entanglement, quantum algorithms, and quantum computational complexity theory.

78

4 Comments

Joint work with Dhrumil Patel and Patrick Coles now published in Quantum - the open journal for quantum science: https://lnkd.in/g7vUGDjn Popular Summary: Many real-world problems in science and industry can be expressed as optimization problems, which involve finding the best solution while meeting specific constraints. Among these, a special class of optimization problems called semidefinite programming holds significance. They are widely used to model or approximate problems arising in various fields such as operations research, combinatorial optimization, control theory, and quantum information theory. For solving these programs, quantum algorithms have been proven to provide a quadratic speedup over classical algorithms. However, these quantum algorithms are not well-suited for current quantum devices, which are noisy and limited in their capabilities. In this work, we propose three quantum algorithms designed to run on these noisy devices. Our algorithms are hybrid quantum-classical algorithms that have a classical computer available for optimization, only calling a quantum computer for tasks that are not efficiently solvable by it. We rigorously analyze the performance of one of our algorithms, quantifying how rapidly it converges to the optimal value. Finally, to demonstrate their practicality, we numerically simulate our quantum algorithms for problems like MaxCut, a prominent graph theoretic problem. Our simulations showcase their effectiveness even in the presence of noise.

106

Interested in solving combinatorial #scheduling problems with differentiable models and gradient descent on GPUs, TPUs, or other accelerators? Coming at ICML 2024 #ICML, Mingju Liu (Mingju's website: https://lnkd.in/gbyWAwT9 ) present our paper, "Differentiable Combinatorial Scheduling at Scale," where we introduce a fully differentiable modeling approach for combinatorial scheduling. This new formulation allows for a fully differentiable encoding of SDC-scheduling #sdc #scheduling, which can be extended to broader combinatorial problems under linear programming (LP) models. Great thanks to the scheduling/HLS expert Prof. Zhiru Zhang from Cornell for many insightful discussions and advice, and congrats to our leading student authors Mingju Liu Yingjie Li. If you are interested in solving discrete combinatorial problems with differentiable models using ML infrastructures, please check out our paper and GitHub repository, and feel free to reach out! Paper: https://lnkd.in/gFCyGXZX Code: https://lnkd.in/gUik3NuA #ICML2024 #Scheduling #Opensource

118

2 Comments

Check out our latest work on Multi-Task Learning, written by my undergraduate student Daniel Mao, alongside coauthors Yifan Wu, Maximilian Gilles, and Alexander Wong. In this study, we conducted an empirical investigation of multi-task learning in the context of vision for robotic bin picking, utilizing Multi-modal RGB+Depth inputs and addressing seven diverse objectives, including regressions, classifications, and mask predictions. Our findings reveal that not all MTL methods are effective in practice. Our experimental results offer the community deeper insights into the fundamental nature of MTL problems. https://lnkd.in/gyG_ixaX #MTL #Deeplearning

20