Download
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
Project Samples
Categories
Machine LearningLicense
MIT LicenseFollow BPL
Other Useful Business Software
$300 Free Credits for Your Google Cloud Projects
Launch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of BPL!
