Learning a representation by relating selected matching examples or views and contrasting them with other examples. The augmentation, matching and sampling rules determine which distinctions are retained. Brain-like prediction in a trained model does not establish the exact objective or plasticity mechanism in cortex.[ref]
Unsupervised neural network models of the ventral visual stream by Chengxu Zhuang and others. Abstract and Results; PNAS 118, e2014196118: contrastive learning, multi-area prediction and child-view training data
Articles by others on the same topic
There are currently no matching articles.