This shows you the differences between two versions of the page.
Next revision | Previous revision | ||
news:from_machine_learning_to_machine_reasoning [2011/02/09 03:13] leonb created |
news:from_machine_learning_to_machine_reasoning [2011/06/26 21:23] (current) leonb |
||
---|---|---|---|
Line 1: | Line 1: | ||
====== From machine learning to machine reasoning ====== | ====== From machine learning to machine reasoning ====== | ||
- | Over the last couple of years, I progressively formulated | + | Over the last couple of years, I progressively formulated |
about the connection between machine learning and machine reasoning. | about the connection between machine learning and machine reasoning. | ||
I have discussed this idea with many friends and I even gave a seminar in Montreal in 2008. | I have discussed this idea with many friends and I even gave a seminar in Montreal in 2008. | ||
- | It was well time to write this down as a tech report ([[: | + | It is described in this [[: |
- | [[: | + | === Abstract === |
- | Léon Bottou | + | |
+ | |||
+ | [[: | ||
- | // | ||
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, | 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, |