AlexNet
A deep convolutional neural network submitted by Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton to the 2012 ImageNet competition. It reduced the image recognition error rate from 26% to 15.3%, marking a landmark turning point in deep learning history and representing the first large-scale application of GPU parallel computing to neural network training.
Core Facts
In 2012, AlexNet won the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) by a margin of nearly 11 percentage points over the second-place entry, reducing the Top-5 error rate from 26% to 15.3%
AlexNet's victory in the ImageNet competition officially ushered in the era of deep learning.
In 2012, Hinton's team's AlexNet won the ImageNet competition by an overwhelming margin.
Timeline (last 90 days)
The genealogy of computer vision models is more miscellaneous than that of language models, including LeNet, AlexNet, VGG, ResNet, DenseNet, EfficientNet, Vision Transformer, Swin, ConvNeXt, and others, with each architecture solving a specific defect exposed by the previous architecture.
A study systematically compared the performance of five CNN architectures—AlexNet, Inception, LeNet, VGG16 and MobileNet—in detecting twig blight of the Pequi tree (Caryocar brasiliense).
AlexNet was the first to systematically use ReLU instead of Sigmoid/Tanh in a large-scale deep convolutional network, making training deep networks feasible and increasing training speed several times over.
The encoder in the original paper is derived from the first five convolutional layers plus a pooling layer of AlexNet, turning a 227×227 input into a 6×6×256 representation.
AlexNet triggered a paradigm shift in the field of computer vision in 2012.
AlexNet's breakthrough victory in the ImageNet competition in 2012 was built on CUDA acceleration.
In 2012, AlexNet reduced the Top-5 error rate from 25.8% to 16.4% in the ImageNet competition (ILSVRC), trained using two NVIDIA GTX 580 GPUs.
AlexNet adopted an 8-layer deep convolutional neural network architecture, leveraged GPU-accelerated training, and reduced the Top-5 error rate from the previous year's 25.8% to 15.3%.
In 2012, Geoffrey Hinton supervised the development of the AlexNet model at the University of Toronto, which achieved a breakthrough in the ImageNet image recognition challenge.
In 2012, Hinton and his students Alex Krizhevsky and Ilya Sutskever developed the AlexNet model, which achieved breakthrough results in the ImageNet competition.
3 more timeline events
All Facts (17)
In 2012, AlexNet won the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) by a margin of nearly 11 percentage points over the second-place entry, reducing the Top-5 error rate from 26% to 15.3%
90%VerifiedAlexNet's victory in the ImageNet competition officially ushered in the era of deep learning.
90%VerifiedIn 2012, Hinton's team's AlexNet won the ImageNet competition by an overwhelming margin.
80%UnverifiedAlexNet was proposed by Krizhevsky, Sutskever, and Hinton, and won the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) in 2012.
70%UnverifiedThe genealogy of computer vision models is more miscellaneous than that of language models, including LeNet, AlexNet, VGG, ResNet, DenseNet, EfficientNet, Vision Transformer, Swin, ConvNeXt, and others, with each architecture solving a specific defect exposed by the previous architecture.
50%UnverifiedAlexNet was the first to systematically use ReLU instead of Sigmoid/Tanh in a large-scale deep convolutional network, making training deep networks feasible and increasing training speed several times over.
50%UnverifiedThe encoder in the original paper is derived from the first five convolutional layers plus a pooling layer of AlexNet, turning a 227×227 input into a 6×6×256 representation.
50%UnverifiedAlexNet triggered a paradigm shift in the field of computer vision in 2012.
50%UnverifiedAlexNet's breakthrough victory in the ImageNet competition in 2012 was built on CUDA acceleration.
50%UnverifiedIn 2012, AlexNet reduced the Top-5 error rate from 25.8% to 16.4% in the ImageNet competition (ILSVRC), trained using two NVIDIA GTX 580 GPUs.
50%UnverifiedAlexNet adopted an 8-layer deep convolutional neural network architecture, leveraged GPU-accelerated training, and reduced the Top-5 error rate from the previous year's 25.8% to 15.3%.
50%UnverifiedIn 2012, Geoffrey Hinton supervised the development of the AlexNet model at the University of Toronto, which achieved a breakthrough in the ImageNet image recognition challenge.
50%UnverifiedLeCun's LeNet-5 in 1998 was used to recognize handwritten digits, and AlexNet in 2012 ignited the deep learning revolution at the ImageNet competition.
50%Unverified2012年Alex Krizhevsky等人使用AlexNet在ImageNet竞赛中将top-5错误率从26%降低到15.3%，该突破基于两块GTX 580显卡的CUDA加速训练实现
50%UnverifiedCNN架构从LeNet-5到AlexNet（2012）、VGGNet（2014）、GoogLeNet/Inception（2014）、ResNet（2015），再到EfficientNet和ConvNeXt经历了演进过程
50%UnverifiedA study systematically compared the performance of five CNN architectures—AlexNet, Inception, LeNet, VGG16 and MobileNet—in detecting twig blight of the Pequi tree (Caryocar brasiliense).
50%UnverifiedIn 2012, Hinton and his students Alex Krizhevsky and Ilya Sutskever developed the AlexNet model, which achieved breakthrough results in the ImageNet competition.
50%