Unlike classic nervous networks with solid filters, it uses new model adaptable masks – they change the form depending on the task and they are better adjusted to deterioration.
The result is a higher accuracy and lower calculation load. Moreover, as the tests show, the internal logic of the model is surprisingly similar to the activity of the visual shell of the mice.
The method has already been tested for Alexnet and Repkettet and the authors themselves will be useful in medicine, robots and autopilots. Sources and models are organized in Github and the study itself will be presented at the ICLR 2025 Conference.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
