René Reboh’s research while affiliated with HP Inc. and other places

... Unfortunately, this particular statement, which is similar to others we have encountered elsewhere, has no factual basis. [19] Dendral's team even suggested that the lack of feedback they got from users was an indication of successful use (rather than -as most producers of programs would realise -a lack of use of the program) by writing: ...

Reference:

The rise and fall of the legal expert system†† Previously published in Leith P., ‘The rise and fall of the legal expert system’, in European Journal of Law and Technology, Vol 1, Issue 1, 2010.View all notes

... Most researchers working on knowledge-based simulation attempt either to couple a numerical simulation tool with an AI knowledge representation language (Holsapple and Whinston 1988), (Klein and Methlie 1995) or to integrate numerical simulation facilities in an AI knowledge representation language (Reboh and Risch 1986), (Gelman et al. 1988). However, the result is in both cases affected by a well-known bottleneck of Copyright © 1998, American Association for Artificial Intelligence (www.aaai.org). ...

Reference:

AMIA: an environment for knowledge-based discrete-time systems simulation

... If we take apart pioneering works like MYCIN and TEIRESIAS (Shortliffe, 1976;Davis and Lenat, 1982 ;Buchanan and Shortliffe, 1984) or PROSPECTOR (see Reboh, 1983), most of the works for developing the explanation capabilities of expert systems do not take into account uncertainty. What is proposed in MYCIN is limited to the treatment of two typeS of questions : "how has this conclusion been established ?", and "why has the system tried to establish this fact?". ...

Reference:

Positive and Negative Explanations of Uncertain Reasoning in the Framework of Possibility Theory

... Typically, database management systems involve a relatively small number of relations or files holding a large number of records, whereas rule-based systems consist of a large number of relationships with a small number of records [63]. Additionally, relational databases essentially represent knowledge in a first-order logic formalism and query languages mostly exploit first-order logic features. ...

Reference:

Large-Scale Legal Reasoning with Rules and Databases

... The loans manager enters data gathered from an interview with the customer and their historic management records into 'Lending Advisor' (LA). The LA DSS then calculates the probability of the loan defaulting, drawing upon data profiles of companies who defaulted on loans in the past (Duda et al 1987). Lending Advisor presented an opportunity to augment managers' local lay knowledge with rational-calculative technique; however, its potential to be used in this way was increasingly compromised as it became drawn into burgeoning rationalization driven through by executive management. ...

Reference:

'Getting the truth': exploring the material grounds of institutional dynamics in social media