feature detector
A unit or neuron in a neural network that is trained to recognize specific patterns or features in input data, such as edges, textures, or more complex patterns
As defined in Possible End of Humanity from AI? Geoffrey Hinton at MIT Technology Review's EmTech Digital
Where it comes up · 1
Most important claims · 3 of 3Search all claims for “feature detector” →
- Back propagation works by computing how each weight in a neural network should change to reduce the discrepancy between desired output and actual output, then changing weights in those directions; the algorithm works backwards through the network to assign credit to each feature detector for helping or hindering correct predictionsPossible End of Humanity from AI? Geoffrey Hinton at MIT Technology Review's EmTech Digital
- Multi-layer neural networks build hierarchical feature detection: initial layers detect simple features (edges), higher layers detect combinations (e.g., two edges forming a beak), and later layers integrate multiple features spatially (e.g., beak and eye in correct relation) to identify objectsPossible End of Humanity from AI? Geoffrey Hinton at MIT Technology Review's EmTech Digital
- Feature detectors in early layers of neural networks detect simple features like edges (contrast between bright and dark regions), detected by having large positive weights for bright pixels and large negative weights for dark neighboring pixels, activating when one side is bright and the other darkPossible End of Humanity from AI? Geoffrey Hinton at MIT Technology Review's EmTech Digital