AI Not as Efficient as Human Configural Shape Perception
A new study suggests that deep convolutional neural networks (DCNNs) do not perceive objects as humans do, which could be risky in real-time AI applications.
Source: azorobotics.com
Stay updated with breaking news from Configural Manner. Get real-time updates on events, politics, business, and more. Visit us for reliable news and exclusive interviews.
A new study suggests that deep convolutional neural networks (DCNNs) do not perceive objects as humans do, which could be risky in real-time AI applications.