Abductive reasoning networks
نویسندگان
چکیده
Is the process of inferring facts using neural networks a unique form of reasoning? Is there really a different type of reasoning separate and distinct from deduction and induction? Does there exist a single fundamental form of inference for reasoning qualitatively, quantitatively, possibilistically (about 'fuzzy' concepts), and probabilistically? YES, it is called abduction. This paper presents abduction and abductory induction. Abduction not only classifies the distinct type of reasoning performed when neural networks are applied, but gives a logical framework for expanding current neural network research to include network concepts not constrained by neuron analogies. These networks are called abductive networks. In describing abductive networks, this paper unveils the 'power' of networks of functional elements. A practical machine learning tool for synthesizing abductive networks from databases of examples, called the Abductory Induction Mechanism (AIMTM), is also presented.
منابع مشابه
Probabilistic properties of model-based diagnostic reasoning in Bayesian networks
So far, much research has been carried out into general Bayesian networks and limited attention has been given to special types of Bayesian networks for specific applications. An example of such an application is model-based diagnosis, i.e. the diagnosis of malfunctioning of devices or systems, based on an explicit model of the structure and behaviour of these devices and systems. Basically, tw...
متن کاملFault Diagnosis of Telecommunication Networks : Realistic Abductive Reasoning Approach
In this paper, we propose a method to diagnose the faults in the telecommunication networks by using the Realistic Abductive Reasoning Model 1]. This model uses abductive inference mechanism based on the parsimonious covering theory with some new features added to the general model of diagnostic problem solving. The fault diagnosis knowledge is assumed to be represented in the form of causal ch...
متن کاملProbabilistic Abduction using Markov Logic Networks
Abduction is inference to the best explanation of a given set of evidence. It is important for plan or intent recognition systems. Traditional approaches to abductive reasoning have either used first-order logic, which is unable to reason under uncertainty, or Bayesian networks, which can handle uncertainty using probabilities but cannot directly handle an unbounded number of related entities. ...
متن کاملTransparent Neural Networks - Integrating Concept Formation and Reasoning
We present the transparent neural networks, a graph-based computational model that was designed with the aim of facilitating human understanding. We also give an algorithm for developing such networks automatically by interacting with the environment. This is done by adding and removing structures for spatial and temporal memory. Thus we automatically obtain a monolithic computational model whi...
متن کاملPartial abductive inference in Bayesian belief networks by simulated annealing
Abductive inference in Bayesian belief networks (BBN) is intended as the process of generating the K most probable con®gurations given observed evidence. When we are only interested in a subset of the network variables, this problem is called partial ab-ductive inference. Due to the noncommutative behaviour of the two operators (sum-mation and maximum) involved in the computational process of s...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Neurocomputing
دوره 2 شماره
صفحات -
تاریخ انتشار 1990