1. Machine Learning - starting pack
- Machine Learning concepts : Learning paradigms (supervised, unsupervised, self-supervised), Foundations concepts (training, testing and validation), Learning objectives( generalisation Vs. overfitting/underfitting, Loss Function)
- Types of Machine Learning (Classification Vs. Clustering, regression linear/logistic, Neural networks, Other algorithms)
2. Deep Learning algorithms and techniques (Introduction to deep learning, CNN, AE vs. PCA ,VAE, GAN, Reinforcement Learning)
3. Focusing on Applications (Examples of DL applied to Computer vision for surveillance, healthcare, cultural heritage, etc.) |