Welcome to the Computational Intelligence Laboratory (CI-Lab) repository! This repository hosts a collection of course materials and implementations focusing on various aspects of computational intelligence and neural networks. Below is an overview of the key components included in this repository.
A basic implementation of a single-layer perceptron used for binary classification tasks.
A more advanced neural network with multiple layers capable of solving complex classification and regression problems.
Various algorithms for clustering, including K-means clustering.
Implementation of Radial Basis Function (RBF) networks, commonly used for function approximation and pattern recognition.
A model of a recurrent artificial neural network that serves as a content-addressable memory system with binary threshold nodes.
RNNs designed for sequence prediction problems such as time series forecasting and natural language processing.
Techniques and implementations for system identification using neural network models.
Each project is contained within its own directory and includes Jupyter Notebooks for easy experimentation and learning. To get started, clone this repository and navigate to the project of interest.