2011/02/09 by Léon Bottou, Leon Bottou, Bottou, Leon · 2 voices · 24 citations
Computer Science · #Artificial Intelligence (cs.AI) #Artificial intelligence #Bayesian Modeling and Causal Inference #Bridge (graph theory) #Character (mathematics) #Computer science #Concatenation (mathematics) #FOS: Computer and information sciences #Inference #Machine Learning (cs.LG) #Machine Learning and Algorithms #Machine Learning and Data Classification #Machine learning #Natural language processing #Probabilistic logic #Programming language #Set (abstract data type) #Simple (philosophy) #Theoretical computer science #cs.AI #cs.LG
paper · pdf · doi:10.48550/arxiv.1102.1808
published in arXiv (Cornell University) (Cornell University) · 15 pages - fix broken pagination in v2
openalex publication_date 2011/02/09 · arxiv published 2011/02/09 · arxiv created 2011/02/11 · arxiv updated 2011/02/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08
A plausible definition of "reasoning" could be "algebraically manipulating previously acquired knowledge in order to answer a new question". This definition covers first-order logical inference or probabilistic inference. It also includes much simpler manipulations commonly used to build large learning systems. For instance, we can build an optical character recognition system by first training a character segmenter, an isolated character recognizer, and a language model, using appropriate labeled training sets. Adequately concatenating these modules and fine tuning the resulting system can be viewed as an algebraic operation in a space of models. The resulting model answers a new question, that is, converting the image of a text page into a computer readable text. This observation suggests a conceptual continuity between algebraically rich inference systems, such as logical or probabilistic inference, and simple manipulations, such as the mere concatenation of trainable learning systems. Therefore, instead of trying to bridge the gap between machine learning systems and sophisticated "all-purpose" inference mechanisms, we can instead algebraically enrich the set of manipulations applicable to training systems, and build reasoning capabilities from the ground up.