REF NETWORKS Julian Clinton Aug 1992 Copyright Integral Solutions Ltd. All Rights Reserved >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> <<<<<<<<<<<<<<<<<<<<< >>>>>>>>>>>>>>>>>>>>>> <<<<<<<<<<<<<<<<<<<<< FUNCTIONS & VARIABLES FOR >>>>>>>>>>>>>>>>>>>>>> <<<<<<<<<<<<<<<<<<<<< MANIPULATING NEURAL NETS >>>>>>>>>>>>>>>>>>>>>> <<<<<<<<<<<<<<<<<<<<< (PART OF LIB NETGENERICS) >>>>>>>>>>>>>>>>>>>>>> <<<<<<<<<<<<<<<<<<<<< >>>>>>>>>>>>>>>>>>>>>> <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< CONTENTS - (Use g to access required sections) -- Stores For Networks -- Saving And Loading -- Deleting Networks -- See Also -- Stores For Networks ------------------------------------------------ nn_neural_nets [property table] Store of neural net records. A neural net is accessed using the name (a word) of the net. nn_net_descriptors [property table] A property table storing the network descriptors. -- Saving And Loading ------------------------------------------------- nn_load_net(NETNAME, FILE) -> NETWORK or [procedure] -nn_load_net- takes the name of a neural network as a word and a filename as a string and attempts to load the neural net structure stored in the file and stores it in -nn_neural_nets- accessed by NETNAME. The function returns the network structure if successfully loaded or false otherwise. nn_save_net(NETNAME, FILE) -> SAVED [procedure] -nn_save_net- takes the name of a neural network as a word and a filename as a string and attempts to save the network in FILE. The function returns the filesize or false according to whether the network was successfully saved or not. -- Deleting Networks -------------------------------------------------- nn_delete_net(NAME) [procedure] Removes the network called NAME from -nn_neural_nets-. If NAME is the same as -nn_current_net- then the value of -nn_current_net- will become false. -- See Also ----------------------------------------------------------- For information on specific network types, see: REF *BACKPROP REF *COMPLEARN For information on network training, see: REF *NETTRAINING --- $popneural/ref/networks --- Copyright Integral Solutions Ltd. 1990. All rights reserved. ---