Convolutional Neural Networks
Hierarchical neural networks with local feature detectors and pooling/subsampling stages for visual and spatial pattern recognition, later trained at scale with backpropagation and GPUs.
Core metadata
- ID: convolutional_neural_networks
- Era: Modern
- First known date: 1980 (exact)
- Region: Japan / NHK Science and Technical Research Laboratories; later global machine-learning research
- Review status: source_checked
- Maturity: established
Prerequisites
Dependents
- None.
Fields
Field lanes
- Artificial Intelligence & Machine Learning: Neural Networks
Node sources
- Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position (Biological Cybernetics, 1980, primary_paper) • Supports: node, maturity
- ImageNet Classification with Deep Convolutional Neural Networks (NeurIPS, 2012, primary_paper) • Supports: node, maturity
Prerequisite edge evidence
Edge/source evidence summary:
- Prerequisite edges: 1
- Average edge confidence: 68%
- Prerequisite sources: 1
- expert_inference: 1
| Prerequisite | Type | Confidence | Evidence level | Note | Sources |
|---|---|---|---|---|---|
| Backpropagation Training (backpropagation_training) | enabling | 68% | expert_inference | Backpropagation Training provides a capability that enables this technology without being the only possible path. |
|
This page is generated from canonical era JSON and is indexable by URL.