Difference between revisions of "Neural network module"
(→Training your own networks) |
(→Functions) |
||
| Line 14: | Line 14: | ||
:Generates a library of simulated DEER data for use in neural network training and validation. | :Generates a library of simulated DEER data for use in neural network training and validation. | ||
;[[deer_resample.m]] | ;[[deer_resample.m]] | ||
| − | :Resamples a | + | :Resamples a DEER trace to fit the number of digitsation points expected by the neural network. |
;[[deernet.m]] | ;[[deernet.m]] | ||
| − | :Uses a curated ensemble of neural networks to extract | + | :Uses a curated ensemble of neural networks to extract the distance distribution from DEER data. |
| + | ;[[deernet_bckg.m]] | ||
| + | :Uses a curated ensemble of neural networks to extract the background signal from DEER data. | ||
;[[elexsys2deernet.m]] | ;[[elexsys2deernet.m]] | ||
:Prepares standard Bruker Elexsys datasets for input into the [[deernet.m]] function. | :Prepares standard Bruker Elexsys datasets for input into the [[deernet.m]] function. | ||
| Line 22: | Line 24: | ||
:Evaluates an ensemble of neural networks and decides which ones are best. | :Evaluates an ensemble of neural networks and decides which ones are best. | ||
;[[process_using.m]] | ;[[process_using.m]] | ||
| − | :Runs | + | :Runs DEER data processing using a specified neural network file. |
;[[train_one_net.m]] | ;[[train_one_net.m]] | ||
:Trains a single neural network using supplied parameters. | :Trains a single neural network using supplied parameters. | ||
| − | |||
| − | |||
''Version 2.2, authors: [[Ilya Kuprov]], [[Steve Worswick]]'' | ''Version 2.2, authors: [[Ilya Kuprov]], [[Steve Worswick]]'' | ||
Revision as of 16:15, 22 August 2018
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
Using DEERNet
Simply feed your DEER data to deernet.m or download DeerAnalysis2018, which is easy to use and has DEERNet integrated.
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
Functions
- deer_lib_gen.m
- Generates a library of simulated DEER data for use in neural network training and validation.
- deer_resample.m
- Resamples a DEER trace to fit the number of digitsation points expected by the neural network.
- deernet.m
- Uses a curated ensemble of neural networks to extract the distance distribution from DEER data.
- deernet_bckg.m
- Uses a curated ensemble of neural networks to extract the background signal from DEER data.
- elexsys2deernet.m
- Prepares standard Bruker Elexsys datasets for input into the deernet.m function.
- netset_curate.m
- Evaluates an ensemble of neural networks and decides which ones are best.
- process_using.m
- Runs DEER data processing using a specified neural network file.
- train_one_net.m
- Trains a single neural network using supplied parameters.
Version 2.2, authors: Ilya Kuprov, Steve Worswick
