skip to main content


Search for: All records

Creators/Authors contains: "Chen, Zhe"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Free, publicly-accessible full text available June 27, 2025
  2. Free, publicly-accessible full text available December 7, 2024
  3. Ever-growing edge applications often require short processing latency and high energy efficiency to meet strict timing and power budget. In this work, we propose that the compact long short-term memory (LSTM) model can approximate conventional acausal algorithms with reduced latency and improved efficiency for real-time causal prediction, especially for the neural signal processing in closed-loop feedback applications. We design an LSTM inference accelerator by taking advantage of the fine-grained parallelism and pipelined feedforward and recurrent updates. We also propose a bit-sparse quantization method that can reduce the circuit area and power consumption by replacing the multipliers with the bit-shift operators. We explore different combinations of pruning and quantization methods for energy-efficient LSTM inference on datasets collected from the electroencephalogram (EEG) and calcium image processing applications. Evaluation results show that our proposed LSTM inference accelerator can achieve 1.19 GOPS/mW energy efficiency. The LSTM accelerator with 2-sbit/16-bit sparse quantization and 60% sparsity can reduce the circuit area and power consumption by 54.1% and 56.3%, respectively, compared with a 16-bit baseline implementation. 
    more » « less
  4. Abstract

    The terminal Ediacaran Shibantan biota (~550–543 Ma) from the Dengying Formation in the Yangtze Gorges area of South China represents one of the rare examples of carbonate-hosted Ediacara-type macrofossil assemblages. In addition to the numerically dominant taxa—the non-biomineralizing tubular fossilWutubusand discoidal fossilsAspidellaandHiemalora, the Shibantan biota also bears a moderate diversity of frondose fossils, includingPteridinium,Rangea,Arborea, andCharnia. In this paper, we report two species of the rangeomorph genusCharnia, including the type speciesCharnia masoniFord, 1958 emend. andCharnia gracilisnew species, from the Shibantan biota. Most of the ShibantanCharniaspecimens preserve only the petalodium, with a few bearing the holdfast and stem. Despite overall architectural similarities to otherCharniaspecies, the Shibantan specimens ofCharnia gracilisn. sp. are distinct in their relatively straight, slender, and more acutely angled first-order branches. They also show evidence that may support a two-stage growth model and a epibenthic sessile lifestyle.Charniafossils described herein represent one of the youngest occurrences of this genus and extend its paleogeographic and stratigraphic distributions. Our discovery also highlights the notable diversity of the Shibantan biota, which contains examples of a wide range of Ediacaran morphogroups.

    UUID:http://zoobank.org/837216cd-4a4a-4e13-89e2-ee354ba48a4c

     
    more » « less