• Santa Clara, CA, United States
Recent publications
This article presents a clock-forwarded, inverter-based short-reach simultaneous bi-directional (ISR-SBD) physical layer (PHY) targeted for die-to-die communication over silicon interposers or similar high-density interconnect. Short-reach links of this type are increasingly important to support larger systems built with chiplets and multiple die and to facilitate the shift to medium-and long-range optical communication based on silicon photonics. This project explores the advantages of simultaneous bi-directional signaling (SBD) over other bandwidth-doubling techniques (e.g., PAM4). Fabricated in a 5-nm standard CMOS process, the ISR-SBD PHY demonstrates 50.4 Gb/s/wire (25.2 Gb/s each direction) and 0.297 pJ/bit on a 750-mV supply over a 1.2-mm on-chip channel.
The energy efficiency of deep neural network (DNN) inference can be improved with custom accelerators. DNN inference accelerators often employ specialized hardware techniques to improve energy efficiency, but many of these techniques result in catastrophic accuracy loss on transformer-based DNNs, which have become ubiquitous for natural language processing (NLP) tasks. This article presents a DNN accelerator designed for efficient execution of transformers. The proposed accelerator implements per-vector scaled quantization (VSQ), which employs an independent scale factor for each 64-element vector to enable the use of 4-bit arithmetic with little accuracy loss and low energy overhead. Using a multilevel dataflow to maximize reuse, the 5-nm prototype achieves 95.6 tera-operations per second per Watt (TOPS/W) at 0.46 V on a 4-bit benchmarking layer with VSQ. At a nominal voltage of 0.67 V, the accelerator achieves 1734 inferences/s/W (38.7 TOPS/W) with only 0.7% accuracy loss on BERT-Base and 4714 inferences/s/W (38.6 TOPS/W) with 0.15% accuracy loss on ResNet-50 by using quantization-aware fine-tuning to recover accuracy, demonstrating a practical accelerator design for energy-efficient DNN inference.
Antimicrobial peptides emerge as compounds that can alleviate the global health hazard of antimicrobial resistance, prompting a need for novel computational approaches to peptide generation. Here, we propose HydrAMP, a conditional variational autoencoder that learns lower-dimensional, continuous representation of peptides and captures their antimicrobial properties. The model disentangles the learnt representation of a peptide from its antimicrobial conditions and leverages parameter-controlled creativity. HydrAMP is the first model that is directly optimized for diverse tasks, including unconstrained and analogue generation and outperforms other approaches in these tasks. An additional preselection procedure based on ranking of generated peptides and molecular dynamics simulations increases experimental validation rate. Wet-lab experiments on five bacterial strains confirm high activity of nine peptides generated as analogues of clinically relevant prototypes, as well as six analogues of an inactive peptide. HydrAMP enables generation of diverse and potent peptides, making a step towards resolving the antimicrobial resistance crisis.
The BioCreative National Library of Medicine (NLM)-Chem track calls for a community effort to fine-tune automated recognition of chemical names in the biomedical literature. Chemicals are one of the most searched biomedical entities in PubMed, and-as highlighted during the coronavirus disease 2019 pandemic-their identification may significantly advance research in multiple biomedical subfields. While previous community challenges focused on identifying chemical names mentioned in titles and abstracts, the full text contains valuable additional detail. We, therefore, organized the BioCreative NLM-Chem track as a community effort to address automated chemical entity recognition in full-text articles. The track consisted of two tasks: (i) chemical identification and (ii) chemical indexing. The chemical identification task required predicting all chemicals mentioned in recently published full-text articles, both span [i.e. named entity recognition (NER)] and normalization (i.e. entity linking), using Medical Subject Headings (MeSH). The chemical indexing task required identifying which chemicals reflect topics for each article and should therefore appear in the listing of MeSH terms for the document in the MEDLINE article indexing. This manuscript summarizes the BioCreative NLM-Chem track and post-challenge experiments. We received a total of 85 submissions from 17 teams worldwide. The highest performance achieved for the chemical identification task was 0.8672 F-score (0.8759 precision and 0.8587 recall) for strict NER performance and 0.8136 F-score (0.8621 precision and 0.7702 recall) for strict normalization performance. The highest performance achieved for the chemical indexing task was 0.6073 F-score (0.7417 precision and 0.5141 recall). This community challenge demonstrated that (i) the current substantial achievements in deep learning technologies can be utilized to improve automated prediction accuracy further and (ii) the chemical indexing task is substantially more challenging. We look forward to further developing biomedical text-mining methods to respond to the rapid growth of biomedical literature. The NLM-Chem track dataset and other challenge materials are publicly available at https://ftp.ncbi.nlm.nih.gov/pub/lu/BC7-NLM-Chem-track/. Database URL https://ftp.ncbi.nlm.nih.gov/pub/lu/BC7-NLM-Chem-track/.
Machine learning (ML) models, if trained to data sets of high-fidelity quantum simulations, produce accurate and efficient interatomic potentials. Active learning (AL) is a powerful tool to iteratively generate diverse data sets. In this approach, the ML model provides an uncertainty estimate along with its prediction for each new atomic configuration. If the uncertainty estimate passes a certain threshold, then the configuration is included in the data set. Here we develop a strategy to more rapidly discover configurations that meaningfully augment the training data set. The approach, uncertainty-driven dynamics for active learning (UDD-AL), modifies the potential energy surface used in molecular dynamics simulations to favor regions of configuration space for which there is large model uncertainty. The performance of UDD-AL is demonstrated for two AL tasks: sampling the conformational space of glycine and sampling the promotion of proton transfer in acetylacetone. The method is shown to efficiently explore the chemically relevant configuration space, which may be inaccessible using regular dynamical sampling at target temperature conditions.
Task offloading is a powerful tool in Mobile Edge Computing (MEC). However, in many practical scenarios, the number of required processing cycles of a task is unknown beforehand and only known until its completion. This poses a serious challenge in making offloading decisions as the number of processing cycles is a key parameter to determine whether a task’s deadline can be met. To cope with such processing uncertainty, we formulate a Chance-Constrained Program (CCP) that offers probabilistic guarantees to task deadlines. The goal is to minimize energy consumption for the users while meeting the probabilistic task deadlines. We assume that only the means and variances of the random processing cycles are available, without any knowledge of distribution functions. We employ a powerful tool called Exact Conic Reformulation (ECR) that reformulates probabilistic deadline constraints into deterministic ones. Subsequently, we design an online solution called EPD (Energy-minimized solution with Probabilistic Deadline guarantee) for periodic scheduling and schedule updates during run-time. We show that EPD can address the processing uncertainty with probabilistic deadline guarantees while minimizing the users’ energy consumption.
This article analyzes visual data captured from five countries and three U.S. states to evaluate the effectiveness of lockdown policies for reducing the spread of COVID-19. The main challenge is the scale: nearly six million images are analyzed to observe how people respond to the policy changes.
Institution pages aggregate content on ResearchGate related to an institution. The members listed on this page have self-identified as being affiliated with this institution. Publications listed on this page were identified by our algorithms as relating to this institution. This page was not created or approved by the institution. If you represent an institution and have questions about these pages or wish to report inaccurate content, you can contact us here.
757 members
Stefan Jeschke
  • Department of Research
John A. Gunnels
  • Mathematical Libraries/Quantum Computing
Karel Petrak
  • Department of Research
2788 San Tomas Expressway, 95051, Santa Clara, CA, United States
+1 (408) 486-2000