BPL

http://github.com/brendenlake/visual-turing-tests, http://github.com/brendenlake/omniglot and http://github.com/brendenlake/BPL

Paper as Webpage: https://www.sciencemag.org/content/350/6266/1332.full Previous short discussion: https://news.ycombinator.com/item?id=10714517 Link to Matlab code on Github: https://github.com/brendenlake/BPL

Paper: https://www.sciencemag.org/content/350/6266/1332.full Code: https://github.com/brendenlake/BPL Abstract: People learning new concepts can often generalize successfully from just a single example, yet machine learning algorithms typically require tens or hundreds of examples to perform with similar accuracy. People can also use learned concepts in richer ways than conventional algorithms—for action, imagination, and explanation. We present a computational model that captures these human learning abilities for a large class of simple visual concepts: handwritten characters from the world’s alphabets. The model represents concepts as simple programs that best explain observed examples under a Bayesian criterion. On a challenging one-shot classification task, the model achieves human-level performance while outperforming recent deep le

For anyone interested this seems to be the code (written in Matlab) that they used to get their results: https://github.com/brendenlake/BPL

Sorry I should have included the link in my post since I searched and found it. https://github.com/brendenlake/BPL.git