Description of LeNet’s Architecture
The LeNet architecture consists of several layers that progressively extract and condense information from input images. Here, is it the description of each layer of the LeNet architecture:
- Input Layer: Accepts 32×32 pixel images, often zero-padded if original images are smaller.
- First Convolutional Layer (C1): Consists of six 5×5 filters, producing six feature maps of 28×28 each.
- First Pooling Layer (S2): Applies 2×2 average pooling, reducing feature maps’ size to 14×14.
- Second Convolutional Layer (C3): Uses sixteen 5×5 filters, but with sparse connections, outputting sixteen 10×10 feature maps.
- Second Pooling Layer (S4): Further reduces feature maps to 5×5 using 2×2 average pooling.
- Fully Connected Layers:
- First Fully Connected Layer (C5): Fully connected with 120 nodes.
- Second Fully Connected Layer (F6): Comprises 84 nodes.
- Output Layer: Softmax or Gaussian activation that outputs probabilities across 10 classes (digits 0-9).
To know more about LeNet Architecture, you can refer to – LeNet-5 Architecture
What is LeNet?
LeNet is a seminal convolutional neural network architecture developed by Yann LeCun and colleagues, pivotal in revolutionizing image recognition through its innovative design and influential principles. The article provides a comprehensive exploration of LeNet, elucidating its architecture, historical context, significance in deep learning, and diverse applications across various domains.
Table of Content
- Understanding LeNet
- Significance of LeNet in Deep Learning
- Historical Context Leading up to the Development of LeNet
- Chronology of LeNet Architecture
- Motivation Behind the Creation of LeNet
- Description of LeNet’s Architecture
- Applications of LeNet
- Conclusion