Artificial neural network created from DNA | KurzweilAI: Using a simple DNA gate architecture that allows experimental scale-up of multilayer digital circuits, the researchers systematically transformed arbitrary linear threshold circuits (an artificial neural network model) into DNA strand displacement cascades that function as small neural networks.
That approach enabled them to implement a Hopfield associative memory with four fully connected artificial neurons made from 112 distinct DNA strands. After training in silico, it remembers four single-stranded DNA patterns and recalls the most similar one when presented with an incomplete pattern.
No comments:
Post a Comment