EasyDeepLearn

What made AlexNet (2012) a breakthrough?

easy

Answer

  • AlexNet: 8 layers, ReLU activations (huge speedup vs sigmoid), dropout (novel regularization), overlapping max pooling, local response normalization (LRN, now obsolete), heavy data augmentation, and GPU training split across 2 GTX 580s.
  • Won ImageNet 2012 by 10+ percentage points — kicked off the deep-learning revolution and made GPUs mandatory for vision.
Check yourself — multiple choice
  • AlexNet used sigmoid + no dropout
  • 8 layers with ReLU + dropout + GPU training + heavy augmentation — kicked off the DL era in vision
  • Same as LeNet
  • AlexNet had zero data augmentation

AlexNet: ReLU + dropout + GPU + augmentation → deep learning's ImageNet breakthrough.

#architectures#computer-vision

Practise Deep Learning

214 interview questions in this topic.

Related questions