BPL (Bayesian Program Learning) is a MATLAB implementation of the Bayesian Program Learning framework for one-shot concept learning (especially on handwritten characters). The approach treats each concept (e.g. a character) as being generated by a probabilistic program (motor primitives, strokes, spatial relationships), and inference proceeds by fitting those generative programs to a single example, generalizing to new examples, and generating new exemplars. The repository contains code for parsing stroke sequences, fitting motor programs, exemplar generation, classification, re-fitting, and demonstration scripts.
Features
- Motor program / stroke fitting to interpret character generation
- One-shot classification (given one example, classify novel ones)
- Exemplar generation (produce novel variants of a concept)
- Re-fitting of models (adjust generative programs for new data)
- Demo scripts illustrating parsing, classification, exemplar generation
- Support functions for generative priors, optimization, stroke utilities
Categories
Machine LearningLicense
MIT LicenseFollow BPL
Other Useful Business Software
MongoDB Atlas runs apps anywhere
MongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of BPL!