Learning from targets or constraints derived from the data or their transformations rather than externally supplied semantic labels. The supervision source and permitted transformations are part of the hypothesis. Contrastive representation learning is one family of such methods.
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.