Эта нейросетевая модель использует ограниченные машины Больцмана для создания нелинейных генеративных образов лиц. Алгоритм обучается без учителя, находя скрытые закономерности, что позволяет ИИ эффективно распознавать личности даже при сравнении сложных пар изображений.
We describe a neurally-inspired, unsupervised learning algorithm that builds a non-linear generative model for pairs of face images from the same individual. Individuals are then recognized by finding the highest relative probability pair among all pairs that consist of a test image and an image whose identity is known. Our method compares favorably with other methods in the literature. The generative model consists of a single layer of rate-coded, non-linear feature detectors and it has the property that, given a data vector, the true posterior probability distribution over the feature detector activities can be inferred rapidly without iteration or approximation. The weights of the feature detectors are learned by com(cid:173) paring the correlations of pixel intensities and feature activations in two phases: When the network is observing real data and when it is observing reconstructions of real data generated from the feature activations.