TEC - AI Machine Learning

Artificial Intelligence (Machine Learning & NSA Mode)

Explore the world of Artificial Intelligence through the lens of Machine Learning and NSA (Neural Symbolic AI) Mode. This course introduces core AI concepts, teaching you how machines learn from data to make predictions, automate tasks, and uncover insights. You’ll gain hands-on experience with machine learning models, algorithms, and neural-symbolic integration techniques — equipping you with the skills to develop intelligent systems that combine the power of data-driven learning with symbolic reasoning.

This module covers the basics of Artificial Intelligence (AI), introducing concepts like machine learning and neural networks. Participants will learn how AI algorithms work, focusing on the key components of deep learning and its applications in modern technologies. The module provides foundational knowledge of AI tools and techniques, preparing participants for more advanced roles in AI development and implementation.

This course is specifically designed to provide participants with :

Gain an in-depth knowledge of what artificial intelligence is, its historical evolution, and its various applications in today's world.
Understand the basics of machine learning, including key concepts, algorithms, and practical applications.
Learn about the structure and functioning of neural networks, and explore deep learning architectures such as CNNs and RNNs.
Get familiar with popular tools and libraries used in AI and machine learning, and apply them through practical, real-world projects.
Discuss the ethical implications of AI, including bias, privacy, and the impact on employment.

MODULE 1 : Introduction to Artificial Intelligence

Definition and History.

What is AI?.
The history of AI: Key Milestones.
Turing Test & its significance.
Narrow AI vs. General AI.
Strong AI vs. Weak AI. Applications of AI
AI in healthcare, finance, education, and more.
Case studies and real-world examples.
Bias in AI.
The role of AI in job displacement.
Privacy concerns and AI regulations.

MODULE 2 : Introduction to Machine Learning

Basic Concepts.

What is machine learning ?
Types of machine learning : supervised, unsupervised, and reinforcement learning.
The ML pipeline : data collection, preprocessing, model training, evaluation, and deployment.

Supervised Learning.

Regression vs. classification.
Common algorithms: linear regression, logistic regression, decision trees, and support vector machines.

Unsupervised Learning.

Clustering vs. Association.
Common algorithms: k-means, hierarchical clustering, and apriori algorithm.

Reinforcement Learning.

Key concepts : agents, environments, and rewards.
Exploration vs. exploitation.
E-learning and policy gradients.

Tools and Libraries.

Introduction to popular ML tools: scikit-learn, TensorFlow, and PyTorch.
Practical examples and hands-on projects.

MODULE 3 : 5G NR Call Processing (NSA Mode)

Basics of Neural Networks.

Biological inspiration: the human brain.
Structure of a neural network: neurons, layers, and activation functions.
Forward propagation and backpropagation.

Deep Learning Architectures.

Introduction to deep learning.
Convolutional neural networks (CNNs) and their applications in image processing.
Recurrent neural networks (RNNs) and their applications in sequence data.
Generative adversarial networks (GANs) and their use cases.