Jan Vitek

Just published today, our paper on DigiSpan. Two things I am pleased about: 1. DigiSpan is more accurate than the live-voice digit span memory testing that has been used for decades, that it hopefully replaces. 2. It is being used clinically in several countries even before the paper was published. The median time between research showing that a clinical tool is useful and it being taken up clinically is 17 years! https://lnkd.in/gjFKKHYc

142

9 Comments

📢 Our new paper "Higher-Order GNNs Meet Efficiency: Sparse Sobolev Graph Neural Networks" has been accepted in IEEE Transactions on Signal and Information Processing over Networks! This work introduces sparse Sobolev graph neural networks (S2-GNN) to address a key challenge in scaling up GNNs. While traditional GNNs typically rely on immediate node neighbors, limiting their effectiveness in capturing complex graph relationships, S2-GNN employs higher-order, sparse filters to efficiently handle large graphs. Our key contributions: Spectral insights: We reveal a spectral similarity between higher-order Laplacians and their sparse approximations, which supports the design of high-performing yet efficient GNNs. Architecture: S2-GNN leverages cascades of sparse filters to enable accurate updates in node embeddings without excessive computational costs. Robustness: We provide stability analysis of S2-GNN, demonstrating robustness to graph perturbations. Extensive benchmarking: S2-GNN consistently outperforms or competes with leading GNN methods across diverse datasets and tasks. We hope this work contributes to advancing scalable, high-efficiency GNN architectures for real-world applications. 🔗 Preprint: https://lnkd.in/eAJJ9SAD 🔗 Code: https://lnkd.in/eWK7XZM2 Thanks to my co-authors Aref Einizade, Andjela Todorovic, Jhon Castro-Correa, Mohsen Badiey, Thierry Bouwmans, and Fragkiskos Malliaros. This work was supported by ANR, the French National Research Agency, Office of Naval Research, Hi! PARIS Center - AI for Science, Business & Society, Télécom Paris, Institut Polytechnique de Paris, University of Delaware, La Rochelle Université, CentraleSupélec, Université Paris-Saclay, and Inria. #GraphNeuralNetworks #SparseGNN

64

9 Comments

In this new paper we explore the use of classical programming techniques in implementing the quantum lattice Boltzmann method in the Intel Quantum SDK. https://lnkd.in/gpDSFe6b

14

Here is our new paper accepted in Neurocomputing journal. SITU: Stochastic input encoding and weight update thresholding for efficient memristive neural network in-situ training The Analog-to-Digital Converter (ADC) sensing and conductance update are the most power-demanding processes in the in-situ training of memristive neural networks. In this work, we propose a new thresholded weight update method in conjunction with stochastic input encoding to reduce the ADC sensing requirement and weight updates. This leads to better power and area efficiency for simple neural network models developed in situ on memristive crossbars. This is an interesting research work by Xuening Dong and collaboration between University of Toronto, James Cook University , and York University. https://lnkd.in/gY4-GgtC

57

1 Comment

The off-line lectures of my Computational Microelectronics course this semester have concluded. This year, I have introduced several new features: 1) Simple instruction set (L1) 2) Compact model for MOSFETs (L2~L5) 3) Neural network (L8 & L9) 4) Level-set method (L20 & L21) 5) Monte Carlo method for ion implantation (L22) 6) Thermal expansion (L23) The entire playlist of live-streamed (or pre-recorded) videos is available on YouTube: https://lnkd.in/g-CmNeu6 The lecture slides and materials can be downloaded from my GitHub repository: GitHub - hi2ska2/cm2024f Some of newly introduced topics have been covered briefly, and I plan to improve their treatment in the coming years. Additionally, I will continue to expand the course coverage to stay aligned with the advancements in computation microelectronics.

70

5 Comments

Happy about our latest paper titled "Deduplicator: When Computation Reuse Meets Load Balancing at the Network Edge", which was recently accepted for publication by IFIP Networking 2024. All the props go to my senior Ph.D. student, Md. Washik Al Azad. This is the 9th (!) publication during his Ph.D., which is a substantial accomplishment for a systems student. The rest of his papers have been published at IEEE PerCom (best paper runner up award), the IEEE Internet of Things Journal (impact factor > 10), IEEE CLOUD, and the IEEE Wireless Communications Magazine (impact factor > 10), among other venues. In this paper, we explore whether we can achieve the contradictory in nature functions of load balancing and computation reuse at the network edge. To this end, we propose an edge middlebox, called the Deduplicator. Our experimental results demonstrate that we can facilitate computation reuse and distribute the load among edge servers at the same time. You can find a preprint of our paper on arXiv: https://lnkd.in/dkQqq9XM Our code is also available on GitHub: https://lnkd.in/dq3HXJSZ #research #cloudcomputing #edgecomputing #loadbalancing #distributedsystems #systems #computernetworks #middleboxes

45

6 Comments

Our paper, "DRAMScope: Uncovering DRAM Microarchitecture and Characteristics by Issuing Memory Commands," was accepted at ISCA 2024! We had an intriguing journey to figure out the sizes of DRAM MATs, common pitfalls regarding address and data mapping in the computer architecture community, coupled-row activation, and RowHammer/RowPress characteristics induced by the 6F^2 DRAM cell structure, to list a few, by issuing ordinary commands to DRAM. We look forward to presenting our paper in Buenos Aires, Argentina. I am really proud of my students and colleagues, without whom I could not imagine to publish this work in a one-and-done manner. Pdf: https://lnkd.in/gnnQS_XA Authors: Hwayong Nam, Seungmin Baek, Minbok Wi, Michael Jaemin Kim, Jaehyun Park, Chihun Song, Nam Sung Kim, and Jung Ho Ahn Abstract: The demand for precise information on DRAM microarchitectures and error characteristics has surged, driven by the need to explore processing in memory, enhance reliability, and mitigate security vulnerability. Nonetheless, DRAM manufacturers have disclosed only a limited amount of information, making it difficult to find specific information on their DRAM microarchitectures. This paper addresses this gap by presenting more rigorous findings on the microarchitectures of commodity DRAM chips and their impacts on the characteristics of activate-induced bitflips (AIBs), such as RowHammer and RowPress. The previous studies have also attempted to understand the DRAM microarchitectures and associated behaviors, but we have found some of their results to be misled by inaccurate address mapping and internal data swizzling or lack of a deeper understanding of the modern DRAM cell structure. For accurate and efficient reverse engineering, we use three tools: AIBs, retention time test, and RowCopy, which can be cross-validated. With these three tools, we first take a macroscopic view of modern DRAM chips to uncover the size, structure, and operation of their subarrays, memory array tiles (MATs), and rows. Then, we analyze AIB characteristics based on the microscopic view of the DRAM microarchitecture, such as 6F^2 cell layout, through which we rectify misunderstandings regarding AIBs and discover a new data pattern that accelerates AIBs. Lastly, based on our findings at both macroscopic and microscopic levels, we identify previously unknown AIB vulnerabilities and propose a simple yet effective protection solution.

154

3 Comments

[PAPER UPDATE] Excited to announce that our paper "When In-Memory Computing Meets Spiking Neural Networks: From Applications to Circuits" has been published in #AppliedPhysicsReviews! 🔥Curious about the trade-offs that shape cutting-edge designs? How do neuro-inspired spiking neural networks (SNNs) algorithms and In-memory Computing (IMC) revolutionize the future of AI? This paper dives deep into their synergies, investigating the complex interactions between accuracy, energy, latency, and area. Major Contributions: - Comprehensive overview of SNNs + IMC applications & circuits powering neuromorphic computing. - Exploiting SNN temporal sparsity for analog IMC with massive PPA gains—featuring #SpikeSim, an SNN-specific IMC architecture. - Tackling NVM non-idealities in IMC crossbars with solutions like noise-aware batchnorm, ensuring robust SNN inference. - Challenging the myth: "More NVM precision = better," highlighting trade-offs in energy efficiency, and area. -Future-forward insights on online learning, emerging neuronal devices, and co-exploration to drive energy-efficient IMC-SNN in next-gen AI hardware. Authors: Abhishek Moitra Abhiroop Bhattacharjee Yuhang Li Youngeun Kim Paper Link: https://lnkd.in/eDtFavrg SpikeSim Code: https://lnkd.in/eBz5ZnRD #NeuromorphicComputing #InMemoryComputing #SpikingNeuralNetworks #APR #CoDesign Center for the Co-Design of Cognitive Systems

157

1 Comment

I am proud to share that our paper, "Greedy Recursive Spectral Bisection for Modularity-Bound Hierarchical Divisive Community Detection," has been published in Statistics and Computing. Thanks to an agreement between Springer and FCT - Portugal, you can access the full article for free! Dive into our innovative approach for community detection and explore the detailed methodology and results. Check it out here: https://rdcu.be/dL8bM #StatisticsAndComputing #CommunityDetection #Research #OpenAccess #Springer #PPCIC #PPPRO #CEFETRJ #DataScience

30

Some believe (myself included) that Linear Types are essential for safe programming in the real world. Rust succeeded to place the idea at work in the mainstream, witnessing the overwhelming impact of far reaching fundamental research in logic and computation in computing practice for everyone to see. All this started by a paper by Jean-Yves Girard (accepted without reviewing by the editor due to its extreme originality) in the journal Theoretical Computer Science back in 1987 (https://lnkd.in/dCmnPajd).

23

New paper published in Physical Review Applied. we propose pulse-based variational quantum optimization that uses direct pulse control to optimize quantum states in SQUIDs, enhanced by metalearning for efficient problem-solving on quantum devices. https://lnkd.in/dBa2M2_e

26

Our #icra2024 paper is now available from #ieee dl. We proposed a new Inverse Reinforcement Learning based method for hand trajectory prediction. Mukund Mitra Gyanig K. Partha Pratim Chakrabarti

18

2 Comments

𝐌𝐮𝐬𝐭-𝐫𝐞𝐚𝐝, 𝐟𝐫𝐞𝐞 𝐛𝐨𝐨𝐤 𝐭𝐡𝐚𝐭 𝐩𝐫𝐨𝐯𝐢𝐝𝐞𝐬 𝐚 𝐩𝐚𝐭𝐡𝐰𝐚𝐲 𝐟𝐫𝐨𝐦 𝐆𝐀𝐈 𝐭𝐨 𝐀𝐆𝐈! ​ Yann LeCun has expressed skepticism about the potential of LLMs to achieve Artificial General Intelligence (AGI), citing limitations in memory, planning, and grounding in real-world understanding. However, we argue that 𝗟𝗟𝗠 𝗖𝗼𝗹𝗹𝗮𝗯𝗼𝗿𝗮𝘁𝗶𝘃𝗲 𝗜𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝗰𝗲 (𝗟𝗖𝗜)—particularly with multiple multimodal LLMs working together—offers a promising architecture to address these challenges and progress toward AGI. ​ Two key architectural innovations underlie LCI: ​ 𝐒𝐞𝐩𝐚𝐫𝐚𝐭𝐢𝐨𝐧 𝐨𝐟 𝐔𝐧𝐜𝐨𝐧𝐬𝐜𝐢𝐨𝐮𝐬 𝐏𝐫𝐨𝐜𝐞𝐬𝐬𝐢𝐧𝐠 𝐚𝐧𝐝 𝐂𝐨𝐧𝐬𝐜𝐢𝐨𝐮𝐬 𝐑𝐞𝐚𝐬𝐨𝐧𝐢𝐧𝐠 𝐚𝐧𝐝 𝐏𝐥𝐚𝐧𝐧𝐢𝐧𝐠: Inspired by the human mind’s dual-layer structure, LCI divides its architecture into foundational and adaptive layers. The foundation layer, akin to unconscious processing, leverages extensive datasets to build robust pattern recognition, encoding essential responses much like human instincts. The adaptive layer, mirroring conscious thought, enables rapid adaptation and contextual reasoning. This dual-layer approach allows LLMs to perform complex tasks with foundational knowledge while adjusting to new information on the fly, much as a child learns new concepts within a developed cognitive framework. ​ 𝐃𝐢𝐬𝐭𝐢𝐧𝐜𝐭 𝐑𝐨𝐥𝐞𝐬 𝐟𝐨𝐫 𝐄𝐚𝐜𝐡 𝐋𝐋𝐌-𝐀𝐠𝐞𝐧𝐭: Each LLM-agent is assigned a specific role, such as executive (knowledge processing), legislative (behavior guardrails), and judicial (adapting to cultural norms). ​ Additionally, our validation of the LCI framework has been thoroughly tested through real-world deployment in applications across various domains, including healthcare, sales planning, investment, and debiasing news. These empirical deployments highlight the practical viability and adaptability of the LCI framework, showcasing its ability to enhance reasoning and decision-making through collaborative intelligence. ​ The eleven aphorisms presented in this free book illustrate the philosophical foundation of the LCI framework, backed by empirical studies. Through LCI, we envision a clear pathway to AGI, rooted in collaborative intelligence and flexible, context-aware adaptation. https://lnkd.in/gn74DkNj (free) https://lnkd.in/gszSvfqP ($6.98 printing fee)

9

The latest release of the simdutf C++ library (6.0.0) brings in more convenience for C++20 users. While you used to have to provide both a pointer and a size parameter... often you can now just pass your container... std::vector<char> data{1, 2, 3, 4, 5}; // C++11 API auto cpp11 = simdutf::autodetect_encoding(data.data(), data.size()); // C++20 API auto cpp20 = simdutf::autodetect_encoding(data);

17

Shut the backdoors in neural networks! GuardianMPC is the first muliparty computation (MPC)-based countermeasure against backdoor attacks that  🛑 does *not* adversely affect the training accuracy, 🧮 supports private training, ☄️ offers accelerated oblivious inference on FPGAs.  Stay tuned for the paper to appear in IEEE Access. The code and author version of the paper are here: https://lnkd.in/eSVerRVk Congratulations to Mohammad Hashemi, my Ph.D. student, for building GuardianMPC. A big thank you to Domenic Forte, our great collaborator. #ai #backdoor #mpc

55

Pleased to share our new work entitled "Reshaping the ISAC Tradeoff Under OFDM Signaling: A Probabilistic Constellation Shaping Approach" accepted by the IEEE Transactions on Signal Processing, where we investigated the sensing performance of OFDM-ISAC signals modulated with PSK/QAM symbols. The random communication data embedded in the OFDM signal results in severe variability in the sidelobes of its ambiguity function (AF), which leads to missed detection of weak targets and false detection of ghost targets, thereby impairing the sensing performance. To cope with this issue, we characterized the random AF of OFDM communication signals, and proposed a probabilistic constellation shaping (PCS) approach to maximize the achievable information rate (AIR) while controlling the variance of the sensing AF. The paper has just been published online in the IEEE TSP. You may wish to check more details at: https://lnkd.in/gz6jwydM #ISAC #6G #SignalProcessing

79

4 Comments

I bumped into my 2017 CppCon keynote “Learning and Teaching Modern C++ ”. Then, I hit many key points about how to use contemporary C++ well, and highlighted several problems we had to solve. https://lnkd.in/e-PsinSr Since then, we have not moved as far or as fast as I hoped.

787

26 Comments

Are you facing hurdles in scaling up your computational tasks or fine-tuning deep learning models on distributed memory systems with GPU acceleration? Join us at JuliaCon 2024 for the Dagger.jl Workshop! Discover how Dagger's parallel task-based runtime can empower you to efficiently parallelize across threads, nodes, and GPUs. Secure your spot now! 🌟 JuliaCon 2024 #JuliaLang #JuliaCon2024 #ParallelComputing #Daggerjl #GPUComputing

11