matlab - In Convolutional Neural Networks (CNN), how we can decide number of kernels between input and hidden layer? - Cross Validated

I have $32\times32$ input image and $5\times5$ convolution. So in the first hidden layer, the feature map size will be $28\times28$. At this link we can see in C1, the number of feature maps is 4 b...

matlab - In Convolutional Neural Networks (CNN), how we can decide number of kernels between input and hidden layer? - Cross Validated Stack Internal Knowledge at work Bring the best of human thought and AI automation together at your work. Explore Stack Internal In Convolutional Neural Networks (CNN), how we can decide number of kernels between input and hidden layer? Ask Question Asked 10 years, 5 months ago Modified 4 years, 3 months ago Viewed 22k times 4 $\begingroup$ I have $32\times32$ input image and $5\times5$ convolution. So in the first hidden layer, the feature map size will be $28

related reading

• CS231n Deep Learning for Computer Visioncs231n.github.io
• A Beginner's Guide To Understanding Convolutional Neural Networks – Adit Deshpande – Engineering at Forward | UCLA CS '19adeshpande3.github.io
• 7.4. Multiple Input and Multiple Output Channels — Dive into Deep Learning 1.0.3 documentationd2l.ai
• Convolutional Neural Networks, Explained | Towards Data Sciencetowardsdatascience.com
• Computing Receptive Fields of Convolutional Neural Networksdistill.pub
• Zoom In: An Introduction to Circuitsdistill.pub
• A Beginner's Guide To Understanding Convolutional Neural Networks Part 2 – Adit Deshpande – Engineering at Forward | UCLA CS '19adeshpande3.github.io
• Toy Models of Superpositiontransformer-circuits.pub
• Neural networks and deep learningneuralnetworksanddeeplearning.com
• Feature Visualizationdistill.pub
• Convolutional Neural Network (CNN) | TensorFlow Coretensorflow.org
• A Recipe for Training Neural Networkskarpathy.github.io