Receptive Field
Understand receptive fields in CNNs — how convolutional layers expand their field of view, the gap between theoretical and effective receptive fields, and strategies for controlling RF growth.
6 min readConcept
Tagged with
neural-networks
Explore machine learning concepts related to neural-networks. Clear explanations and practical insights.
5
Concepts Found
Concepts Related to neural-networks
He/Kaiming Initialization
Learn He (Kaiming) initialization for ReLU neural networks: understand why ReLU needs special weight initialization, visualize variance flow, and see dead neurons in action.
7 min readConcept
Xavier/Glorot Initialization
Learn Xavier (Glorot) initialization: how it balances forward signals and backward gradients to enable stable deep network training with tanh and sigmoid.
8 min readConcept
Batch Normalization
Learn batch normalization in deep learning: how normalizing layer inputs accelerates training, improves gradient flow, and acts as regularization with interactive visualizations.
7 min readConcept
Skip Connections
Learn how skip connections and residual learning enable training of very deep neural networks. Understand the ResNet revolution with interactive visualizations.
9 min readConcept