Neural Networks and Intelligent Computing Systems

Welcome to the course repository for Neural Networks and Intelligent Computing Systems, part of the Undergraduate Program (9th semester) at the School of Electrical and Computer Engineering, National Technical University of Athens.

Course Overview

This repository contains code, resources, and projects related to the course Neural Networks and Intelligent Computing Systems. The course covers fundamental and advanced concepts in Neural Networks, Unsupervised Learning, and Deep Learning, emphasizing both theoretical foundations and hands-on implementations.

This project involved the application of various machine learning and deep learning techniques, including:

• Supervised Learning: Implemented Naive Bayes, k-Nearest Neighbors (k-NN), and cross-validation for classification tasks. Worked with parametric and non-parametric classifiers, addressing bias-variance trade-off and hyperparameter tuning.
• Unsupervised Learning: Applied clustering techniques like k-means, fuzzy c-means, Gaussian Mixture Models, and Self-Organizing Maps (SOM) to uncover patterns in data. Evaluated clustering performance using relevant metrics.
• Reinforcement Learning: Developed models using Q-learning and deep reinforcement learning for decision-making processes.
• Deep Learning: Built neural networks with TensorFlow and Keras, focusing on convolutional networks (CNNs), recurrent networks (RNNs), and residual networks for complex data representations.

Table of Contents

• Exercises
  • Neural Networks
  • Unsupervised Learning
  • Deep Learning

The following tools and technologies are used in the exercises and projects:

• Programming Language: Python
• Libraries:
  • TensorFlow / PyTorch
  • Keras
  • Scikit-learn
  • NumPy, Pandas
  • Matplotlib / Seaborn for data visualization