goingDeeperWithConvolutions: Difference between revisions
| Line 1: | Line 1: | ||
= Introduction = | = Introduction = | ||
In the last three years, due to the advances of deep learning and more concretely convolutional networks. [http://white.stanford.edu/teach/index.php/An_Introduction_to_Convolutional_Neural_Networks [an introduction of CNN]] , the quality of image recognition has increased dramatically. The error rates for ILSVRC competition dropped significantly year by year.[http://image-net.org/challenges/LSVRC/ [LSVRC]] This paper proposed a new deep convolutional neural network architecture codenamed Inception. With the inception module and carefully crafted design researchers build a 22 layers deep network called Google Lenet, which uses 12X fewer parameters while being significantly more accurate than the winners of ILSVRC 2012. [http://www.cs.toronto.edu/~fritz/absps/imagenet.pdf [1]] | In the last three years, due to the advances of deep learning and more concretely convolutional networks. [http://white.stanford.edu/teach/index.php/An_Introduction_to_Convolutional_Neural_Networks [an introduction of CNN]] , the quality of image recognition has increased dramatically. The error rates for ILSVRC competition dropped significantly year by year.[http://image-net.org/challenges/LSVRC/ [LSVRC]] This paper proposed a new deep convolutional neural network architecture codenamed Inception. With the inception module and carefully crafted design researchers build a 22 layers deep network called Google Lenet, which uses 12X fewer parameters while being significantly more accurate than the winners of ILSVRC 2012. [http://www.cs.toronto.edu/~fritz/absps/imagenet.pdf [1]] | ||
= Related work = | |||
In paper [http://arxiv.org/pdf/1312.4400v3.pdf [2]] Lin et al. pointed out that the convolution filter in CNN is a generalized linear model (GLM) for the underlying data patch and the level of abstraction is low with GLM. They suggested replacing GLM with a ”micro network” structure which is a general nonlinear function approximator. | |||
Revision as of 15:56, 20 October 2015
Introduction
In the last three years, due to the advances of deep learning and more concretely convolutional networks. [an introduction of CNN] , the quality of image recognition has increased dramatically. The error rates for ILSVRC competition dropped significantly year by year.[LSVRC] This paper proposed a new deep convolutional neural network architecture codenamed Inception. With the inception module and carefully crafted design researchers build a 22 layers deep network called Google Lenet, which uses 12X fewer parameters while being significantly more accurate than the winners of ILSVRC 2012. [1]
Related work
In paper [2] Lin et al. pointed out that the convolution filter in CNN is a generalized linear model (GLM) for the underlying data patch and the level of abstraction is low with GLM. They suggested replacing GLM with a ”micro network” structure which is a general nonlinear function approximator.