A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, et al.
This paper demonstrates that residual connections accelerate Inception network training and improve accuracy, achieving 3.08% top-5 error on ImageNet with an ensemble.
Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton
AlexNet achieved state-of-the-art image classification on ImageNet using a deep CNN with 60M parameters, ReLU, GPU training, and dropout.
Unknown
ConvNets (NFNets) match Vision Transformers in performance when pre-trained on large datasets and fine-tuned on ImageNet, challenging the assumption that ViTs are inherently superior at scale.
Ruoqian Lin, Rui Zhang, Chunyang Wang, et al.
This paper presents a deep-learning library and models for robust atom segmentation, localization, denoising, and deblurring in atomic-resolution STEM images, outperforming conventional methods.
Esteban Real, Alok Aggarwal, Yanping Huang, et al.
First evolutionary algorithm to produce an image classifier (AmoebaNet-A) surpassing human-crafted designs, achieving state-of-the-art ImageNet accuracy.