GoogleNet

Software / App

Introduced the 'inception module', allowing for more efficient and effective training by using multiple convolution sizes simultaneously.

Mentioned in 3 videos

Videos Mentioning GoogleNet

MIT 6.S094: Computer Vision

MIT 6.S094: Computer Vision

Lex Fridman

Introduced the 'inception module', allowing for more efficient and effective training by using multiple convolution sizes simultaneously.

Deep Learning for Computer Vision (Andrej Karpathy, OpenAI)

Deep Learning for Computer Vision (Andrej Karpathy, OpenAI)

Lex Fridman

A convolutional neural network architecture from 2014 that achieved state-of-the-art results on ImageNet with fewer parameters than VGGNet by using inception modules and removing fully connected layers.

Sequence to Sequence Deep Learning (Quoc Le, Google)

Sequence to Sequence Deep Learning (Quoc Le, Google)

Lex Fridman

A neural network architecture mentioned for image representation in image captioning.