ImageNet classification with deep convolutional neural networks Article Swipe
YOU?
·
· 2017
· Open Access
·
· DOI: https://doi.org/10.1145/3065386
· OA: W2163605009
We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0%, respectively, which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overfitting in the fully connected layers we employed a recently developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.
ImageNet, a tapestry of pixels, vivid and bright,
where deep currents of knowledge flow, unseen in the light.
Classification dances, a rhythm of thought,
640, 000 neurons breathe life, as battles are fought.
In layers of convolution, patterns emerge,
from chaos to clarity, we find our urge.
Eager to learn, each image a voice,
in the silence of data, we make our choice.
Top-1 error rates, a challenge to break,
seeking the truth in the choices we make.
With dropout as armor, we forge ahead,
reviving the hope in the lives that we’ve led.
Artificial wisdom, a mirror of us all,
reflecting our struggles, our rise, and our fall.
Through networks of meaning, we reach for the sky,
ImageNet, our canvas, where dreams never die.
ImageNet.
