OpenAI Blog · Mar 4, 2021
Multimodal neurons in artificial neural networks
Reviewed by Errol Vogt, Site support technician & online learning analyst · original summary · editorial policy
Multimodal neurons in artificial neural networks. We’ve discovered neurons in CLIP that respond to the same concept whether presented literally, symbolically, or conceptually. This may explain CLIP’s accuracy in classifying surprising visual renditions of concepts, and is also an important step toward understanding the associations and biases that CLIP and similar models learn. This update is relevant for small-office operators tracking changes in their tools.
Operator takeaway: For operators: review whether 'Multimodal neurons in artificial neural networks' affects your current setup before relying on it in production.
ai phone