Symbol Structures in Connectionist Networks: Five Properties and Two Architectures
نویسندگان
چکیده
We define five properties of symbol representations (called the Five M's) that together provide a powerful and flexible symbol processing facility. Our ideal symbol structures arc Mobile, Memorable, Meaningful, Malleable, and Modifiable. Conventional symbol processing architectures, such as Lisp on von Neumann machines, support some of these properties, but others seem to require flexibility and an ability to generalize that is unique to connectionist models. Two recently-developed connectionist architectures, BoltzCONS and micro-KLONE, are described in some detail. The representations used in these two architectures satisfy different subsets of the Five M's.
منابع مشابه
Computational modeling of dynamic decision making using connectionist networks
In this research connectionist modeling of decision making has been presented. Important areas for decision making in the brain are thalamus, prefrontal cortex and Amygdala. Connectionist modeling with 3 parts representative for these 3 areas is made based the result of Iowa Gambling Task. In many researches Iowa Gambling Task is used to study emotional decision making. In these kind of decisio...
متن کاملThe Acquisition of New Categories through Grounded Symbols: An Extended Connectionist Model
Solutions to the symbol grounding problem, in psychologically plausible cognitive models, have been based on hybrid connectionist/symbolic architectures, on robotic approaches and on connectionist only systems. This paper presents new simulations on the use of neural network architectures for the grounding of symbols on categories. In particular, the connectivity patterns between layers of the ...
متن کاملSymbol Processing Systems, Connectionist Networks, and Generalized Connectionist Networks
Many authors have suggested that SP (symbol processing) and CN (connectionist network) models offer radically, or even fundamentally, different paradigms for modeling intelligent behavior (see Schneider, 1987) and the design of intelligent systems. Others have argued that CN models have little to contribute to our efforts to understand intelligence (Fodor & Pylyshyn, 1988). A critical examinati...
متن کاملNeurosymbolic integration: unified versus hybrid approaches
Since the mid-1980s, researchers have been pursuing the goal of neurosymbolic integration, i.e., the construction of systems capable of both symbolic and neural processing. We distinguish two major avenues toward this goal: the uniied and the hybrid approaches. Whereas the uniied approach claims that full symbol processing functionalities can be achieved via neural networks alone, the hybrid ap...
متن کاملNeurosymbolic Integration: Uniied versus Hybrid Approaches
Since the mid-1980s, researchers have been pursuing the goal of neurosymbolic integration, i.e., the construction of systems capable of both symbolic and neural processing. We distinguish two major avenues toward this goal: the uniied and the hybrid approaches. Whereas the uniied approach claims that full symbol processing functionalities can be achieved via neural networks alone, the hybrid ap...
متن کامل