Publications by authors named "Daniela Mihai"
Recent work suggests that changing convolutional neural network (CNN) architecture by introducing a bottleneck in the second layer can yield changes in learned function. To understand this relationship fully requires a way of quantitatively comparing trained networks. The fields of electrophysiology and psychophysics have developed a wealth of methods for characterizing visual systems that permit such comparisons.
View Article and Find Full Text PDFArticle Synopsis
- Massive vaginal bleeding is a critical emergency that gynecologists must address promptly.
- If traditional haemostatic treatments fail, uterine artery embolization can effectively stop the bleeding through a minimally invasive approach.
- A case study highlights the successful use of uterine artery embolization in managing massive vaginal bleeding in a patient with cervical cancer.