ECE447 Neuro-Fuzzy Computing

The course covers mainly the area of neural networks, and briefly it covers other relevant fields of the computational intelligence realm, such as fuzzy systems. In particular is studies the following topics:

• Basic concepts and arxhitectures of neuranl networks (NN)
• Neural learning
• Feedforward NN
• Perceptron
• Multilayer backpropagation NN
• Hopfield, Boltzmann NN
• Self-organizing NN
• Deep architectures of NN
• Elements of fuzzy logic
• Elements of fuzzy sets/subsets

The course introduces the theory and practice of neural and fuzzy computation. The course begins with an overview of information processing principles in biological systems. The core of the course consists of the theory and properties of major neural network algorithms and architectures, as well as the basis of fuzzy logic and fuzzy subset theory. The students will have a chance to implement and try out several of these models on practical problems (by using tensorflow, keras. By the end of the course, students will be able to assess the applicability of neural networks for a given task, select an appropriate neural network paradigm, and build a working neural network model for the task.