The researchers replaced synaptic plasticity with memory-based plasticity and found that this did not affect the dynamics of the model, allowing them to reproduce the effects in brain experiments such as memory tests and neuronal responses.
According to project participant Sergei Stasenko, this result will increase the functional properties of neural networks and their energy efficiency when used in neuromorphic chips.
Further implementation of these results could include creating a true neural network architecture that can reproduce biological functions such as memory.
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.
