Why Software Fails and Why AI cannot Help

It was once widely believed that computers would enhance the speed, reliability, and applicability of human deductive reasoning in the physical and social sciences, much as motorized vehicles (e.g., cars, trains, airplanes) have enhanced the speed, reliability, and applicability of human manual abilities in transportation. Yet, 60 years later, computers can be used confidently only for paperwork tasks, analysis of regularly structured data, and simple process control applications. Complex software rarely satisfies user needs, is untrustworthy and difficult to maintain, and largely opaque to its users. Artificial intelligence (AI) methods including heuristics, machine learning, and statistical methods are in opposition to sound deductive reasoning. This presentation explains certain practical and logical impediments to computer enhancement of human deductive reasoning, the deductive limitations of modern programming languages, the role of AI, and provides some promising alternatives.
Speaker(s): David Fisher,
Agenda:
4 pm – Introductions, Start of talk,
5 pm – End of talk, Q&A
5:15 pm – End of event
Room: M 218, Bldg: Buell Building, 21000 West Ten Mile Road, Southfield, Michigan, United States, 48075