AI::Ca...er::SVM(3pm)

💖 AI::Categorizer::Learner::SVM ✨

okay bestie, welcome to the AI::Categorizer::Learner::SVM page, straight out of your friendly neighborhood User Contributed Perl Documentation 🫶 this is the Support Vector Machine Learner and she is that girl 💅

---

🌸 NAME 🌸

AI::Categorizer::Learner::SVM — the Support Vector Machine Learner 🦋

---

✨ SYNOPSIS ✨

no thoughts, just vibes and a little code, bestie:

  use AI::Categorizer::Learner::SVM;

  # Here $k is an AI::Categorizer::KnowledgeSet object

  my $l = new AI::Categorizer::Learner::SVM(...parameters...);
  $l->train(knowledge_set => $k);
  $l->save_state('filename');

  ... time passes ...

  $l = AI::Categorizer::Learner->restore_state('filename');
  while (my $document = ... ) {  # An AI::Categorizer::Document object
    my $hypothesis = $l->categorize($document);
    print "Best assigned category: ", $hypothesis->best_category, "\n";
  }

see how ... time passes ... ? that's the main character arc, honestly 😭 save your state, come back later, restore it, keep categorizing. no notes. 💯

---

🎀 DESCRIPTION 🎀

so this class is a Support Vector Machine machine learner — and yes, that's a mouthful, it's giving "machine learner machine learner", we said what we said 💀 — and it's built on top of Cory Spencer's Algorithm::SVM module. 🌟

and ngl, the tea is: in lots of the recent academic literature, SVMs perform very well for text categorization. lowkey iconic behavior from a math thing. 📚✨

---

💅 METHODS 💅

this class inherits from the AI::Categorizer::Learner class, so all of its methods are available too, unless we explicitly mention otherwise right here. periodt. 👑

🌈 new()

Creates a new SVM Learner and hands it back to you, wrapped in a little bow 🎀

On top of the parameters that the AI::Categorizer::Learner class already accepts, the SVM subclass is also down to accept these:

• svm_kernel — tells it what type of kernel should be used when building the SVM. the default is 'linear'. the possible values are 'linear', 'polynomial', 'radial' and 'sigmoid'. pick your fighter, bestie 🥊

🌟 train(knowledge_set => $k)

Trains the categorizer. this is the glow-up prep arc — it gets everything ready so it can categorize documents later. 💪

the knowledge_set parameter must provide an object of the class AI::Categorizer::KnowledgeSet (or a subclass of it), and that object needs to be populated with lots and lots of documents and categories. like, feed her, she's hungry 🍓

for the deets on how to actually create such an object, go peek at AI::Categorizer::KnowledgeSet.

🦋 categorize($document)

Returns an AI::Categorizer::Hypothesis object representing the categorizer's "best guess" about which categories the given document should be assigned to. 🔮

wanna know how to use that object? AI::Categorizer::Hypothesis has all the details. go read it, i'll wait 💜

👑 save_state($path)

Saves the categorizer so you can use it later. this one is inherited from AI::Categorizer::Storable. 💾

not me romanticizing a serialization method but the way she preserves your whole trained self for later? that's commitment fr fr 😭🫶

---

🌸 AUTHOR 🌸

Ken Williams, ken@mathforum.org ✨

---

🎀 COPYRIGHT 🎀

Copyright 2000-2003 Ken Williams. All rights reserved.

This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself. 🐪💖

---

⭐ SEE ALSO ⭐

• AI::Categorizer(3)
• Algorithm::SVM(3)

go follow them, they're mutuals 🫶

---

and that's the whole page, bestie!! 🌈 this was perl v5.42.0, dated 2025-07-25, and it lives in the User Contributed Perl Documentation section. slay, ate, no crumbs left. 💅✨🎀