US Patent Application 18204363. NEURAL NETWORKS IMPLEMENTED WITH DSD CIRCUITS simplified abstract
Contents
NEURAL NETWORKS IMPLEMENTED WITH DSD CIRCUITS
Organization Name
MICROSOFT TECHNOLOGY LICENSING, LLC
Inventor(s)
Karin Strauss of Seattle WA (US)
Johannes Staffan Anders Linder of Seattle WA (US)
NEURAL NETWORKS IMPLEMENTED WITH DSD CIRCUITS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18204363 titled 'NEURAL NETWORKS IMPLEMENTED WITH DSD CIRCUITS
Simplified Explanation
- This patent application describes a method of implementing neural networks using DNA strand displacement (DSD) circuits. - The neural networks are designed and trained using computer simulations, considering the behavior of DSD circuits. - Oligonucleotides, which are short DNA or RNA molecules, are synthesized and combined to create the neural network. - The neural network described in this implementation is a binary neural network, where each neuron's output is a binary value and the weight of each neuron either maintains or flips the binary value. - The inputs to the neural network can be synthetic oligonucleotides containing digital data or natural oligonucleotides like mRNA. - The outputs from the neural network can be read directly by sequencing the oligonucleotides or by generating signals through the release of fluorescent reporters.
Original Abstract Submitted
Neural networks can be implemented with DNA strand displacement (DSD) circuits. The neural networks are designed and trained in silico taking into account the behavior of DSD circuits. Oligonucleotides comprising DSD circuits are synthesized and combined to form a neural network. In an implementation, the neural network may be a binary neural network in which the output from each neuron is a binary value and the weight of each neuron either maintains the incoming binary value or flips the binary value. Inputs to the neural network are one more oligonucleotides such as synthetic oligonucleotides containing digital data or natural oligonucleotides such as mRNA. Outputs from the neural networks may be oligonucleotides that are read by directly sequencing or oligonucleotides that generate signals such as by release of fluorescent reporters.
