Table of Contents

1. Introduction to AlexNet
2. Walkthrough of AlexNet’s Architecture
3. Training of AlexNet
4. Summary of AlexNet

---

1. Introduction to AlexNet

AlexNet was a deep neural network that was developed by Alex Krizhevsky and others in 2012. It was designed to classify images for the ImageNet LSVRC-2010 competition, where it achieved state of the art results [1]. It also worked with multiple GPUs. The AlexNet model contained 11 layers, they were:

1. Layer C1: Convolution Layer (96, 11×11)
2. Layer S2: Max Pooling Layer (3×3)
3. Layer C3: Convolution Layer (256, 5×5)
4. Layer S4: Max Pooling Layer (3×3)
5. Layer C5: Convolution Layer (384, 3×3)
6. Layer C6: Convolution Layer (384, 3×3)
7. Layer C7: Convolution Layer (256, 3×3)
8. Layer S8: Max Pooling Layer (3×3)
9. Layer F9: Fully-Connected Layer (4096)
10. Layer F10: Fully-Connected Layer (4096)
11. Layer F11: Fully-Connected Layer (1000)

#data-science #artificial-intelligence #machine-learning #convolutional-network