This video contains two lectures
Lecture 1. Supervised and Unsupervised learning
This lecture introduces the fundamental distinction between supervised and unsupervised learning. We explore how learning problems can be formulated from data, how models are trained, and how their performance can be evaluated. The lecture covers regression, classification, clustering, dimensionality reduction, generalization, and the importance of evaluating machine-learning models on data that was not used during training.
Topics Covered
Machine learning and learning from data
Supervised learning
Training data, validation data, and test data
Regression
Classification
Model fitting and prediction
Loss functions and model evaluation
Generalization and overfitting
Unsupervised learning
Clustering
Dimensionality reduction and representations
Learning Goals
Explain what machine learning is and why learning from data is useful for AI systems.
Distinguish between supervised and unsupervised learning.
Explain the difference between regression and classification.
Understand the role of training, validation, and test data.
Understand the concepts of model fitting, loss, and prediction.
Explain why a model that performs well on training data may perform poorly on unseen data.
Understand the concepts of generalization and overfitting.
Explain how clustering can be used to discover structure in unlabeled data.
Understand the purpose of dimensionality reduction and compact data representations.
Lecture 2. Neural Networks and Deep Learning
Neural Networks and Deep Learning are among the most influential technologies behind modern Artificial Intelligence. This lecture introduces the basic concepts of artificial neural networks, how they learn from data, and how deep learning architectures have transformed fields such as image recognition, natural language processing, and generative AI.
Topics Covered
Introduction to Neural Networks
Artificial neurons
Network architectures
Training neural networks
Backpropagation
Deep Learning
Applications of neural networks in AI
Learning Goals
Understand the motivation behind artificial neural networks.
Explain the structure of a neural network.
Describe how learning occurs through training data.
Understand the role of activation functions and network layers.
Explain the difference between shallow and deep learning models.
Recognize common applications of deep learning techniques.