A gentle introduction to deep learning for graphs

D Bacciu, F Errica, A Micheli, M Podda - Neural Networks, 2020 - Elsevier
The adaptive processing of graph data is a long-standing research topic that has been lately
consolidated as a theme of major interest in the deep learning community. The snap …

Deep learning methods for object detection in smart manufacturing: A survey

HM Ahmad, A Rahimi - Journal of Manufacturing Systems, 2022 - Elsevier
Object detection for industrial applications refers to analyzing the captured images and
videos and finding the relationship between the detected objects for better optimization, data …

Greedy layerwise learning can scale to imagenet

E Belilovsky, M Eickenberg… - … conference on machine …, 2019 - proceedings.mlr.press
Shallow supervised 1-hidden layer neural networks have a number of favorable properties
that make them easier to interpret, analyze, and optimize than their deep counterparts, but …

Why should we add early exits to neural networks?

S Scardapane, M Scarpiniti, E Baccarelli… - Cognitive Computation, 2020 - Springer
Deep neural networks are generally designed as a stack of differentiable layers, in which a
prediction is obtained only after running the full stack. Recently, some contributions have …

Revisiting locally supervised learning: an alternative to end-to-end training

Y Wang, Z Ni, S Song, L Yang, G Huang - arxiv preprint arxiv:2101.10832, 2021 - arxiv.org
Due to the need to store the intermediate activations for back-propagation, end-to-end (E2E)
training of deep networks usually suffers from high GPUs memory footprint. This paper aims …

From immunology to artificial intelligence: revolutionizing latent tuberculosis infection diagnosis with machine learning

LS Li, L Yang, L Zhuang, ZY Ye, WG Zhao… - Military Medical …, 2023 - Springer
Latent tuberculosis infection (LTBI) has become a major source of active tuberculosis (ATB).
Although the tuberculin skin test and interferon-gamma release assay can be used to …

Decoupled greedy learning of cnns

E Belilovsky, M Eickenberg… - … Conference on Machine …, 2020 - proceedings.mlr.press
A commonly cited inefficiency of neural network training by back-propagation is the update
locking problem: each layer must wait for the signal to propagate through the network before …

Monitoring social distancing through human detection for preventing/reducing COVID spread

MA Ansari, DK Singh - International Journal of Information Technology, 2021 - Springer
COVID-19 is a severe epidemic that has put the world in a global crisis. Over 42 Million
people are infected, and 1.14 Million deaths are reported worldwide as on Oct 23, 2020. A …

A local–global dual-stream network for building extraction from very-high-resolution remote sensing images

H Zhang, Y Liao, H Yang, G Yang… - IEEE transactions on …, 2020 - ieeexplore.ieee.org
Buildings constitute one of the most important landscapes in remote sensing (RS) images
and have been broadly analyzed in a wide range of applications from urban planning to …

Early-exit deep neural network-a comprehensive survey

H Rahmath P, V Srivastava, K Chaurasia… - ACM Computing …, 2024 - dl.acm.org
Deep neural networks (DNNs) typically have a single exit point that makes predictions by
running the entire stack of neural layers. Since not all inputs require the same amount of …