AIMS AND LEARNING OUTCOMES

The aim of the course is to provide the basis for the design and development of classification and regression software algorithms. The student is introduced to different concepts of machine learning (linear models, decision trees, ensemble learning, artificial neural networks, etc.) and supported through extensive exercises during lectures exploiting several software library in Python (NumPy, Pandas, SciKitLearn e TensorFlow). The last part of the course will be focused on the model deployment on embedded systems.

TEACHING METHODS

The course is composed of a set of frontal lessons and a set of practice sessions. During the frontal lesson, the teacher presents the topics providing also examples of live code that are tested on a Jupyter notebook. Students can use their own laptops during the lecture in order to reproduce what is proposed by the teacher. During the practice sessions, the students have to face up with real problems that they should solve by applying the techniques learnied during the lectures.

SYLLABUS/CONTENT

Part 1 - Fundamental algorithms and techniques
Introduction
Regression
Classification
Linear Models
Decision trees
Ensemble Learning
Dimensionality Reduction
Unsupervised algorithms

Part 2 - Neural Networks
Perceptron
MLP
Backpropagation
Convolutional networks
Advanced Vision

Part 3 - Deployment on embedded devices
Inference
Quantization
TensorFlow Lite and TensorFlow Micro
Deployment on NVidia Jetson platform
TinyML

RECOMMENDED READING/BIBLIOGRAPHY

1. Hands-on Machine Learning with Scikit-Learn, Keras and TensorFlow
2. Papers with Code
3. The Elements of Statistical Learning
4. Data Science from Scratch
5. Neural Networks for Machine Learning