Current implementation, after latest fixes/improvements, works with incremental training, if just one item is added to the training set the model is trained incrementally but the whole file must be rewritten, there is no way to save the model to a different structure other then a file atm.' I have the plugin in production with few thousands mailboxes and it looks promising even if it needs a bit to train, maybe neuralnetwork_min_spam_count and neuralnetwork_min_ham_count default values are too low. I will verify accuracy improvements of the model and tweaks default values if needed. Giovanni
On 2/25/26 2:59 AM, Kent Oyer wrote:
I haven't had time to play with this plugin, but my understanding of this type of NN is that it doesn't work well with incremental training. Meaning that if just one item is added to the training set, the whole learning process needs to be re-run. Otherwise the model adjusts it's weights to match the new sample at the expense of all previous samples. I'm just wondering if you've run into this and if you have any preliminary accuracy statistics from this plugin. On Tue, Dec 30, 2025 at 03:33 AM, Giovanni Bechis <[email protected]> wrote: ------------------------------------------------------------------------------------------------------------------ CAUTION: External email from: gbechis@apache.org Use caution before clicking on links or opening attachments. ------------------------------------------------------------------------------------------------------------------ Hi, I've just committed to my Github repo the first version of a SpamAssassin plugin that uses Neural Networks to detect spam messages. Code is available at https://github.com/bigio/spamassassin-NeuralNetwork <https://github.com/bigio/spamassassin-NeuralNetwork> , if the community is interested I can work on merging it to the Apache SpamAssassin src tree. Testers are always welcome. Cheers Giovanni-- Giovanni BechisV.P. Apache SpamAssassin [email protected] <mailto:[email protected]>
OpenPGP_signature.asc
Description: OpenPGP digital signature
