AlexNet

AlexNet is the name of a convolutional neural network, invented by Alex Krizhevsky, Ilya Sutskever and Geoffrey Hinton.[1] [2]. AlexNet has had a large impact on the field of machine learning, specifically in the application of deep learning to machine vision. As of 2018 it has been cited over 25,000 times.

AlexNet competed in the ImageNet Large Scale Visual Recognition Challenge[3] in 2012. The network achieved a top-5 error of 15.3%, more than 10.8 percentage points lower than that of the runner up. The original paper's primary result was that the depth of the model was essential for its high performance, which was computationally expensive, but made feasible due to the utilization of GPUs during training.[3]

Network design

AlexNet contained eight layers; the first five were convolutional layers, and the last three were fully connected layers.[4] It used the non-saturating ReLU activation function, which showed improved training performance over tanh and sigmoid.[3]

AlexNet was originally written with CUDA to run with GPU support.

References

  1. ↑ "The data that transformed AI research—and possibly the world".
  2. ↑ "ILSVRC2012 Results".
  3. 1 2 3 "ImageNet Classification with Deep Convolutional Neural Networks" (PDF).
  4. ↑ https://cs231n.github.io/convolutional-networks/#case

ImageNet Classification with Deep Convolutional Neural Networks

This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.