Results 11 to 20 of about 14,169,777 (290)
Scaling Up Models and Data with t5x and seqio [PDF]
Recent neural network-based language models have benefited greatly from scaling up the size of training datasets and the number of parameters in the models themselves.
Adam Roberts+42 more
semanticscholar +1 more source
Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory [PDF]
Dataset Distillation is a newly emerging area that aims to distill large datasets into much smaller and highly informative synthetic ones to accelerate training and reduce storage.
Justin Cui+3 more
semanticscholar +1 more source
More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity [PDF]
Transformers have quickly shined in the computer vision world since the emergence of Vision Transformers (ViTs). The dominant role of convolutional neural networks (CNNs) seems to be challenged by increasingly effective transformer-based models.
Shiwei Liu+8 more
semanticscholar +1 more source
VeLO: Training Versatile Learned Optimizers by Scaling Up [PDF]
While deep learning models have replaced hand-designed features across many domains, these models are still trained with hand-designed optimizers. In this work, we leverage the same scaling approach behind the success of deep learning to learn versatile ...
Luke Metz+10 more
semanticscholar +1 more source
LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs [PDF]
Recent advance in 2D CNNs has revealed that large kernels are important. However, when directly applying large convolutional kernels in 3D CNNs, severe difficulties are met, where those successful module designs in 2D become surprisingly ineffective on ...
Yukang Chen+4 more
semanticscholar +1 more source
Although low-income countries have recently seen an exponential flourishing of digital health initiatives, the landscape is characterised by a myriad of small pilots that rarely reach scaling, sustainability and wide adoption.
Riccardo Lampariello+1 more
doaj +1 more source
Scaling Up Vision-Language Pretraining for Image Captioning [PDF]
In recent years, we have witnessed significant performance boost in the image captioning task based on vision-language pre-training (VLP). Scale is believed to be an important factor for this advance.
Xiaowei Hu+6 more
semanticscholar +1 more source
To meet the 2030 goal to end all types of malnutrition, thoroughly investigating and addressing context-specific factors of undernutrition is crucial. Therefore, this study assessed the prevalence of undernutrition and associated factors among children ...
Gosa Girma Ararsa+3 more
doaj +1 more source
With a growing consensus on the need to address malnutrition in a comprehensive and multisectoral way, there has been increased attention on the processes and factors for multisectoral nutrition planning to be successful.
Amanda Coile+5 more
doaj +1 more source
This article explores the shifting perceptual scales of racial epistemology and anti-blackness in predictive policing technology. Following Paul Gilroy, I argue that the historical production of racism and anti-blackness has always been deeply entwined ...
Camille Crichlow
doaj +1 more source