| Program | Source File | Description |
|---|---|---|
| concurrent_inferences | concurrent-inferences.f90 | This program demonstrates how to read a neural network from a JSON file and use the network to perform concurrent inferences. |
| learn_addition | learn-addition.F90 | This trains a neural network to learn the following six polynomial functions of its eight inputs. |
| learn_exponentiation | learn-exponentiation.F90 | This trains a neural network to learn the following six polynomial functions of its eight inputs. |
| learn_microphysics_procedures | learn-microphysics-procedures.F90 | Train a neural network proxies for procedures in the Thompson microphysics model in of ICAR (https://github.com/BerkeleyLab/icar). |
| learn_multiplication | learn-multiplication.F90 | This trains a neural network to learn the following six polynomial functions of its eight inputs. |
| learn_power_series | learn-power-series.F90 | This trains a neural network to learn the following six polynomial functions of its eight inputs. |
| print_training_configuration | print-training-configuration.F90 | Demonstrate how to construct and print a training_configuration_t object |
| train_and_write | train-and-write.F90 | This program demonstrates how to train a simple neural network starting from a randomized initial condition and how to write the initial network and the trained network to separate JSON files. The network has two hiden layers. The input, hidden, and output layers are all two nodes wide. The training data has outputs that identically match the corresponding inputs. Hence, the desired network represents an identity mapping. With RELU activation functions, the desired network therefore contains weights corresponding to identity matrices and biases that vanish everywhere. The initial condition corresponds to the desired network with all weights and biases perturbed by a random variable that is uniformly distributed on the range [0,0.1]. |
| train_saturated_mixture_ratio | learn-saturated-mixing-ratio.F90 | This program trains a neural network to learn the saturated mixing ratio function of ICAR. |
| write_read_infer | write-read-infer.F90 | This program demonstrates how to write a neural network to a JSON file, read the same network from the written file, query the network object for some of its properties, print those properties, and use the network to perform inference. The network performs an identity mapping from any non-negative inputs to the corresponding outputs using a RELU activation function. |