With both knowing more and more details about how neurons and complex neural networks work and having serious demand for making performable huge artificial networks, more and more efforts are devoted to build both hardware and/or software simulators and supercomputers targeting artificial intelligence applications, demanding an exponentially increasing amount of computing capacity. However, the inherently parallel operation of the neural networks is mostly simulated deploying inherently sequential (or in the best case: sequential-parallel) computing elements. The paper shows that neural network simulators, (both software and hardware ones), akin to all other sequential-parallel computing systems, have computing performance limitation due to deploying clock-driven electronic circuits, the 70-year old computing paradigm and Amdahl's Law about parallelized computing systems. The findings explain the limitations/saturation experienced in former studies.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6458202 | PMC |
| http://dx.doi.org/10.1186/s40708-019-0097-2 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Automated ultrasonography of hepatocellular carcinoma using discrete wavelet transform based deep-learning neural network.
Med Image Anal
January 2025
Department of Electrical and Computer Engineering, College of Information and Communication Engineering, Sungkyunkwan University, Suwon, 440-746, South Korea. Electronic address:
This study introduces HCC-Net, a novel wavelet-based approach for the accurate diagnosis of hepatocellular carcinoma (HCC) from abdominal ultrasound (US) images using artificial neural networks. The HCC-Net integrates the discrete wavelet transform (DWT) to decompose US images into four sub-band images, a lesion detector for hierarchical lesion localization, and a pattern-augmented classifier for generating pattern-enhanced lesion images and subsequent classification. The lesion detection uses a hierarchical coarse-to-fine approach to minimize missed lesions.
View Article and Find Full Text PDFA comprehensive scoping review on machine learning-based fetal echocardiography analysis.
Comput Biol Med
January 2025
Institute of Biomedical Engineering, University of Oxford, Old Road Campus Research Building, Oxford, OX3 7DQ, UK.
Fetal echocardiography (ultrasound of the fetal heart) plays a vital role in identifying heart defects, allowing clinicians to establish prenatal and postnatal management plans. Machine learning-based methods are emerging to support the automation of fetal echocardiographic analysis; this review presents the findings from a literature review in this area. Searches were queried at leading indexing platforms ACM, IEEE Xplore, PubMed, Scopus, and Web of Science, including papers published until July 2023.
View Article and Find Full Text PDFMachine learning outperforms humans in microplastic characterization and reveals human labelling errors in FTIR data.
J Hazard Mater
December 2024
Discipline of Chemistry, The University of Newcastle, University Drive, Newcastle, New South Whales 2308, Australia; School of Chemistry, Monash University, Wellington Road, Melbourne, Victoria 3800, Australia. Electronic address:
Microplastics are ubiquitous and appear to be harmful, however, the full extent to which these inflict harm has not been fully elucidated. Analysing environmental sample data is challenging, as the complexity in real data makes both automated and manual analysis either unreliable or time-consuming. To address challenges, we explored a dense feed-forward neural network (DNN) for classifying Fourier transform infrared (FTIR) spectroscopic data.
View Article and Find Full Text PDFSpatially constrained hyperpolarized 13C MRI pharmacokinetic rate constant map estimation using a digital brain phantom and a U-Net.
J Magn Reson
January 2025
UC Berkeley - UCSF Graduate Program in Bioengineering, 1700 4th St, San Francisco, CA 94158, USA; Radiology and Biomedical Imaging, University of California, San Francisco, 1700 4th St, San Francisco, CA 94158, USA.
Fitting rate constants to Hyperpolarized [1-C]Pyruvate (HP C13) MRI data is a promising approach for quantifying metabolism in vivo. Current methods typically fit each voxel of the dataset using a least-squares objective. With these methods, each voxel is considered independently, and the spatial relationships are not considered during fitting.
View Article and Find Full Text PDFSpiking-PhysFormer: Camera-based remote photoplethysmography with parallel spike-driven transformer.
Neural Netw
January 2025
Tsinghua University, Beijing, China. Electronic address:
Artificial neural networks (ANNs) can help camera-based remote photoplethysmography (rPPG) in measuring cardiac activity and physiological signals from facial videos, such as pulse wave, heart rate and respiration rate with better accuracy. However, most existing ANN-based methods require substantial computing resources, which poses challenges for effective deployment on mobile devices. Spiking neural networks (SNNs), on the other hand, hold immense potential for energy-efficient deep learning owing to their binary and event-driven architecture.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!