Knowledge-based artificial neural networks
Artificial Intelligence
Symbolic Representation of Neural Networks
Computer - Special issue: neural computing: companion issue to Spring 1996 IEEE Computational Science & Engineering
Extract intelligible and concise fuzzy rules from neural networks
Fuzzy Sets and Systems - Fuzzy systems
Toward a generalized theory of uncertainty (GTU): an outline
Information Sciences—Informatics and Computer Science: An International Journal
Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series)
Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series)
Extracting symbolic knowledge from recurrent neural networks---A fuzzy logic approach
Fuzzy Sets and Systems
A study of particle swarm optimization particle trajectories
Information Sciences: an International Journal
Interpretation of artificial neural networks by means of fuzzy rules
IEEE Transactions on Neural Networks
Hi-index | 0.01 |
The studies on interpretability of neural networks have been playing an important role in understanding the knowledge developed through their learning and promoting the use of neurocomputing in practical problems. The rule-based setting in which neural networks are interpreted provides a convenient way of expressing knowledge in a transparent and modular manner and at a desired level of granularity (specificity). In this study, we formulate a certain engineering-based style of interpretation in which a given neural network is represented as a collection of local linear models where such models are developed around a collection of linearization nodes. The notion of multi-linearization of neural networks captures the essence of the proposed interpretation. We formulate the problem as an optimization of (i) a collection of linearization nodes around which individual linear models are formed and (ii) aggregation of the individual linearizations, where the linearization fields are subject to optimization. Given the non-differentiable character of the problem, we consider the use of population-based optimization of Particle Swarm Optimization (PSO). Numeric experiments are provided to illustrate the main aspects of the multi-linearization of neural networks.