Lessons from connectionism in differentiating knowledge types

Recent progress in the field of computational creativity has supplied an unanticipated model of the neurobiological knowledge management system known as the brain. Close examination of this model offers an alternative language for the field of knowledge management as well as a means for implementing cognitive agents coming closer than ever to emulating human intelligence and consciousness. Knowledge management (KM) theorists have proposed a number of frameworks for distinguishing different types of knowledge. Oftentimes we hear distinctions such as explicit versus tacit1, content-based or relational2, or new contrasted with established knowledge3. With close to three decades experience in emulating cognitive function in neural networks, the author finds such delineations interesting, to say the least, foreseeing a general debate that mirrors the ongoing dialogue between high- and low-level psychologists: the former group seeks to model human behavior on the basis of beliefs, desires, fears, and hopes, primitives that tend to be as cyclic in definition as KM terms such as 'explicit' or 'tacit'. The latter group takes a totally different tack, asserting as Crick4 did, that all we are, our intelligence, personalities, perhaps even soul, is the outcome of neural mechanics. Such reductionism may ultimately diminish certain mystiques, but the capture, development, sharing, and effectiveness of knowledge is about to enter a boom period exactly because of this new outlook.