Towards Intentional Neural Systems: Experiments with Magnus
نویسندگان
چکیده
Input "Retina" The term "intentionality" arises in connection with natural language understanding in a computer. The problem is not one of speech recognition. It remains a problem even if the words of the language were perfectly encoded by a speech recognizer, or even typed on a keyboard. It is believed that the ability to visualize events when hearing sentences that describe them is a clue to the way in which artificial neural networks need to be structured and trained. The assessment which gives the title to this paper, is that of Searle1 who suggests that classical logical models fail to capture "understanding" as they have no intentional relationship with the objects they represent. Searle illustrated his point with the now well-known example of the Chinese Room where, he argued, the symbols of a language can be manipulated to give answers to questions about a sequence of symbols that make up a story. In this paper we show that, through a process of "iconic" training, a neural state machine can develop an "intentional" representation. An example of this is shown as implemented on MAGNUS (Multiple Automata of General Neural UnitS) software. Figure 1. Net connections for iconic transfer (not all shown).
منابع مشابه
A self-organizing neural network architecture for intentional planning agents
This paper presents a model of neural network embodiment of intentions and planning mechanisms for autonomous agents. The model bridges the dichotomy of symbolic and non-symbolic representation in developing agents. Some novel techniques are introduced that enables the neural network to process and manipulate sequential and hierarchical structures of information. It is suggested that by incorpo...
متن کاملThe emergence of goals in a self-organizing network: A non-mentalist model of intentional actions
A model of intentional actions is presented through the operation of two connected neural networks. A deterministic causal recurrent network relates a random initial state to an ordered final state. A perceptron-like, feed-forward network provides a memory mechanism that links the final states to the original initial states. A non-supervised learning mechanism that selects which final states ar...
متن کاملApplying Pareto Design of GMDH-Type Neural Network for Solid-Liquid Equilibrium of Binary Systems (Isotactic Poly 1-Butene (1)-Organic Solvents (2))
Isotactic poly (1-butene), ipbu-1, was synthesized by using a metallocene catalyst. The thermodynamic phase behavior of polymer–organic solvents systems is very important in every polymer application. In this paper, the solid–liquid equilibrium of ipbu-1 with different organic solvents (1-heptyne, cyclo octane) was studied by a mathematical model. By considering the experiments temperature...
متن کاملExperimental investigation, modeling, and optimization of combined electro-(fenton/coagulation/flotation) process: design of experiments and artificial intelligence systems
In this study, a combined electro-(Fenton/coagulation/flotation) (EF/EC/El) process was studied via degradation of Disperse Orange 25 (DO25) organic dye as a case study. Influences of seven operational parameters on the dye removal efficiency (DR%) were measured: initial pH of the solution (pH0), applied voltage between the anode and cathode (V), initial ferrous ion concentration (CFe), initial...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2007