Home» News» LLCC» 【LLCC】3月18日孙溢凡报告:An introduction to a new learning method

【LLCC】3月18日孙溢凡报告:An introduction to a new learning method

发布日期:2016-03-16 作者:


题目An Introduction to a new learning method








时间2016-03-18 15:10:10




简介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. 

In December last year a paper titled “Human-level concept learning through probabilistic program induction” by Lake et. al. was published as a Science cover story. In this paper, the author presented a computational model that captures some concept learning abilities of human in handwritten characters. The so-called hierarchical bayesian program learning (HBPL) 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 learning approaches. 

发布时间:2016-03-16 09:40:40