Results 21 to 30 of about 495,712 (260)
Frontiers in High Performance ComputingIntroductionHigh-speed x-ray imaging experiments at synchrotron radiation facilities enable the acquisition of spatiotemporal measurements, reaching millions of frames per second.
Songyuan Tang +3 more
doaj +1 more source
Comparative Study on Distributed Lightweight Deep Learning Models for Road Pothole Detection
Sensors, 2023 This paper delves into image detection based on distributed deep-learning techniques for intelligent traffic systems or self-driving cars. The accuracy and precision of neural networks deployed on edge devices (e.g., CCTV (closed-circuit television) for ...
Hassam Tahir, Eun-Sung Jung
doaj +1 more source
Memory-Efficient Batching for Time Series Transformer Training: A Systematic Evaluation
AlgorithmsTransformer-based time series models are being increasingly employed for time series data analysis. However, their training remains memory intensive, especially with high-dimensional data and extended look-back windows, while model-level memory ...
Phanwadee Sinthong +5 more
doaj +1 more source
Therapeutic Apheresis and Dialysis, EarlyView.ABSTRACT Background Establishing a comprehensive apheresis medicine program in a resource‐constrained setting presents significant structural, financial, and logistical challenges. Despite the growing clinical importance of apheresis services globally, published experience from sub‐Saharan Africa remains sparse.
Folasade Adelekan‐Popoola +4 more
wiley +1 more source
Communication Efficient Distributed Training with Distributed Lion
Advances in Neural Information Processing Systems 37The Lion optimizer has been a promising competitor with the AdamW for training large AI models, with advantages on memory, computation, and sample efficiency. In this paper, we introduce Distributed Lion, an innovative adaptation of Lion for distributed training environments.
Bo Liu 0042 +7 more
openaire +3 more sources
Modelling stem cell differentiation related processes—A practical overview for biologists
FEBS Letters, EarlyView.Stem cell differentiation is complex and difficult to control experimentally. This review introduces suitable computational modelling approaches that can support stem cell research, from mechanistic ODE and abstract models to multiscale and deep learning methods.
Ricco Zeegelaar +4 more
wiley +1 more source
Spike train statistics and Gibbs distributions [PDF]
Journal of Physiology-Paris, 2013 23 pages ...
Cessac, Bruno, Cofre, Rodrigo
openaire +4 more sources
Design and analysis strategies for robust microbiome ageing research
FEBS Letters, EarlyView.The gut microbiome changes with age and associates with age‐related morbidity and mortality, establishing it as a potential biomarker and intervention target for ageing. Realising this potential requires methodological rigour, yet distinguishing biological signals from methodological artefacts remains challenging across cohorts. This review provides an
Mark Olenik +5 more
wiley +1 more source
AIThe rapid scaling of large language model (LLM) training has intensified demand for Graphics Processing Unit (GPU) clusters balancing throughput with energy efficiency.
Muhammad Ali Shafique +4 more
doaj +1 more source
Deep Learning Beyond the Training Distribution
, 2021 One of the goals of artificial intelligence is to create machines that can think like humans. Deep learning has been at the core of the remarkable progress made towards this goal. Large artificial neural networks trained on massive datasets can master tasks across vastly different domains. Despite the progress on i.i.d.
openaire +3 more sources