The study showed that there was an interaction between external data and internal conditions in the human brain – for example, from awakening to sleep. This interaction occurs in a specific neuron type that processes information from two sources: external (external stimuli) and internal (context, thoughts, expectations).
Professor Ahsan Adil, the new model of the University of Sterling, imitates this work of the brain. It is called CO4 and is built on the basis of transformers, but with a significant difference: the model selects the most important information before drawing attention to it. This allows you to speed up education and reduce the load in calculations.
CO4 analyzes data according to the “Question – Tip – Hypothesis” scheme. Such an approach repeats human thoughts to solve problems: a person formulates a question, searches and creates possible answers, clarifying them as thought. The model also learns to get more accurate results than the first assumptions.
The tests of the new architecture include tasks in the field of learning, computer vision and understanding of language. The results were encouraging: the model showed high efficiency in lower resource costs.
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.
