2018/04/17 by Guillaume Baudart, Martin Hirzel, Baudart, Guillaume +3 · 2 voices · 8 citations
Computer Science · Psychology · #Artificial intelligence #Bayesian Modeling and Causal Inference #Comparison of multi-paradigm programming languages #Computer science #Deep learning #Explainable Artificial Intelligence (XAI) #Fifth-generation programming language #Inductive programming #Machine Learning and Data Classification #Natural language processing #Probabilistic logic #Programming language #Programming paradigm #Psychology #Second-generation programming language #Strengths and weaknesses #Third-generation programming language #cs.AI #cs.PL
paper · pdf · doi:10.48550/arxiv.1804.06458
published in arXiv (Cornell University) (Cornell University)
arxiv created 2018/04/17 · openalex publication_date 2018/04/17 · arxiv updated 2018/04/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Deep probabilistic programming languages try to combine the advantages of deep learning with those of probabilistic programming languages. If successful, this would be a big step forward in machine learning and programming languages. Unfortunately, as of now, this new crop of languages is hard to use and understand. This paper addresses this problem directly by explaining deep probabilistic programming languages and indirectly by characterizing their current strengths and weaknesses.