main webpage
W Topic
Convolutional Neural Network
Sparse-view CT Reconstruction via Implicit Neural Representation Learning Powered by Dual-Domain Vision Foundation Models
2025
Article

Convolutional Neural Network

Artificial neural network

Convolutional neural network ( CNN ) is a regularized type of feed- forward neural network that learns feature engineering by itself via filters (or kernel) optimization. Vanishing gradients and exploding gradients, seen during backpropagation in earlier neural networks, are prevented by using regularized weights over fewer connections. For example, for each neuron in the fully-connected layer 10,000 weights would be required for processing an image sized 100 × 100 pixels. However, applying cascaded convolution (or cross-correlation) kernels, only 25 neurons are required to process 5x5-sized tiles. Higher-layer features are extracted from wider context windows, compared to lower-layer features.

Exploring foci of:
Sparse-view CT Reconstruction via Implicit Neural Representation Learning Powered by Dual-Domain Vision Foundation Models
2025
Click Convolutional Neural Network Vs:
International Bank For Reconstruction And Development
Learning Curve
Learning Theory (Education)
Experiential Learning
Group Representation
Practice (Learning Method)
Neural Correlates Of Consciousness
Representation Theory Of The Lorentz Group
Learning Environment
Click Convolutional Neural Network Vs:
Machine Learning
Reconstruction Era
Deep Learning
Reinforcement Learning
Learning Standards
Proportional Representation
Attention (Machine Learning)
Recurrent Neural Network
Learning
Click Convolutional Neural Network Vs:
Rectifier (Neural Networks)
Physics-Informed Neural Networks
Learning Disability
Decision Tree Learning
Q-Learning