Neural network module
From Spinach Documentation Wiki
DEERNet is a collection of functions that make and use deep neural networks for processing DEER data. The approach is described in detail in https://dx.doi.org/10.1126/sciadv.aat5218
Training your own networks
- Use deer_lib_gen.m to build a training database.
- Use train_one_net.m repeatedly to create a netset.
- Use netset_curate.m to eliminate low-performance networks.
- Use the resulting netset with deernet.m or deernet_bckg.m
- Generates a library of simulated DEER data for use in neural network training and validation.
- Resamples a DEER trace to fit the number of digitsation points expected by the neural network.
- Uses a curated ensemble of neural networks to extract the distance distribution from DEER data.
- Uses a curated ensemble of neural networks to extract the background signal from DEER data.
- Prepares standard Bruker Elexsys datasets for input into the deernet.m function.
- Evaluates an ensemble of neural networks and decides which ones are best.
- Runs DEER data processing using a specified neural network file.
- Trains a single neural network using supplied parameters.