AlexNet

wikipedia:AlexNet (2012, CUDA) convolutional neural network trends

• https://github.com/computerhistory/AlexNet-Source-Code

Architecture

AlexNet model contains 60 million parameters and 650,000 neurons.

AlexNet contains eight layers: the first five are convolutional layers, some of them followed by max-pooling layers, and the last three are fully connected layers.

Build using 3 Nvidia GTX 580

The ImageNet training set contained 1.2 million images

The model was trained for 90 epochs/passes over a period of five to six days.

Related

• GPU, CUDA, Nvidia GTX 580
• Alex Krizhevsky
• ImageNet
• Ilya Sutskever
• Geoffrey Hinton, University of Toronto
• Yann LeCun

See also

• AlexNet, CNN, Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton, ImageNet, LeNet
• ImageNet, ILSVRC, AlexNet, Ilya Sutskever, Fei-Fei Li
• Artificial neural networks, Neuronal network (NN), CNN, RNN, Micrograd, NPU, ConvNet, AlexNet, GoogLeNet, Apache MXNet, Neural architecture search, DAG, Feedforward neural network, NeurIPS, Feature Pyramid Network, TPU, NPU, Apple Neural Engine (ANE), LLM, TFLOPS, Softmax function, Dilution (neural networks), AlphaGo