Introduction to Machine Learning
The materials intent to cover topics required for the exam in Introduction to Machine Learning.
Theoretical exam
Topics
Materials
- Tests for Artificial General Intelligence
- Techniques for generative AI
- Text to image models
- The computational model for Foraging Ants and the details of its workings
- The Schelling model and it’s working on examples
- Basic ethical frameworks for technology
- Different approaches to machine learning (i.e., supervised, unsupervised and reinforcement learning) and their basic premises, data requirements and limitations
- The basic concept of supervised learning
- Supervised learning by decision trees
- The basic concept of unsupervised learning
- The working mechanism of k-means algorithm
- The mechanism of reinforcement learning
- The Q-learning method
- Deep Learning methods. Value learning and policy learning
- The policy gradient algorithm
- The basic concept of evolutionary algorithms
- Optimization by genetic algorithm
- The basic concept of genetic programming. Differences compared to genetic algorithms
- The basic concept of swarm intelligence
- Optimization by Particle Swarm Optimization
- More recent swarm intelligence techniques. The firefly algorithm
- The basics of neural networks
- Perceptron. Perceptron training
- The basic concept of CRISP-DM
