Sabitlenmiş Tweet

We demonstrate that self-supervised AI can learn rich summary representations of human and mouse brain cell morphology and ultrastructure. These representations have many potential applications, including cell type analysis of brain connectivity. Thanks @sdorkenw and co-authors!
Google AI@GoogleAI
Announcing Segmentation-Guided Contrastive Learning of Representations (SegCLR), a method that trains rich, generic representations of cellular morphology and ultrastructure without manual effort and can identify cell types from only small cell fragments→ goo.gle/3G2uIEh
English


















