AlexNet

Introduced by Krizhevsky et al. in ImageNet Classification with Deep Convolutional Neural Networks

AlexNet is a classic convolutional neural network architecture. It consists of convolutions, max pooling and dense layers as the basic building blocks. Grouped convolutions are used in order to fit the model across two GPUs.

Source: ImageNet Classification with Deep Convolutional Neural Networks

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
General Classification	51	12.66%
Quantization	37	9.18%
Image Classification	31	7.69%
Classification	23	5.71%
Object Detection	22	5.46%
Object Recognition	20	4.96%
Deep Learning	15	3.72%
Object	15	3.72%
Model Compression	12	2.98%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
Convolution	Convolutions
Dense Connections	Feedforward Networks
Dropout	Regularization
Grouped Convolution	Convolutions
Local Response Normalization	Normalization
Max Pooling	Pooling Operations
ReLU	Activation Functions
Softmax	Output Functions

Categories

Add Remove

Convolutional Neural Networks