1. The label used to refer to one of the continuing holy wars in artificial intelligence research. This conflict tangles together two separate issues.One is the relationship between human reasoning and AI; “neats” tend totry to build systems that “reason” in some way identifiably similar to theway humans report themselves as doing, while “scruffies” profess not tocare whether an algorithm resembles human reasoning in the least as longas it works. More importantly, neats tend to believe that logic is king, whilescruffies favour looser, more ad-hoc methods driven by empiricalknowledge. To a neat, scruffy methods appear promiscuous, successful onlyby accident and not productive of insights about how intelligence actuallyworks; to a scruffy, neat methods appear to be hung up on formalism andirrelevant to the hard-to-capture “common sense” of living intelligences.
2. “Neats vs. scruffies” is a sort of characterization used in IT to describe two different approaches to specific disciplines, such as artificial intelligence. The “neats” prefer to advance in a way that is completely documentable and provable, in a method that is clear and logically supported. “Scruffies,” on the other hand, may embrace “fuzzier,” more diverse, or more ambiguous methods that support results. Neats vs. scruffies has also been described as “logical versus analogical” and “symbolic versus connectionist.
3. In general, “neats” use formal methods supported by statistics and built on transparent logic. By contrast, “scruffies” are more likely to embrace things like ad hoc rule making or dynamic algorithms that can be trained to produce the right results. “Neats vs. scruffies” has also been delineated according to different groups of programmers at MIT and other thought centers over the years, as they try to make advances in artificial intelligence. Experts point out that due to the deep philosophical differences between neats and scruffies, neats may view scruffies’ methods as happenstance or insufficiently built, where scruffies might see neats’ methods as being restrictive and limiting to the exploration of the goals in question