View syllabus
ARTIFICIAL INTELLIGENCE II
LETIZIA MILLI
Academic year2023/24
CourseBIOTECHNOLOGIES AND APPLIED ARTIFICIAL INTELLIGENCE FOR HEALTH
Code785AA
Credits6
PeriodSemester 2
LanguageEnglish

ModulesAreaTypeHoursTeacher(s)
ARTIFICIAL INTELLIGENCE IIINF/01LEZIONI48
LETIZIA MILLI unimap
Obiettivi di apprendimento
Learning outcomes
Conoscenze

The course aims to introduce the paradigms to neural networks and deep learning, including the basics of recurrent neural networks and models for complex data, model design and validation, and application to health problems and case studies

 

Knowledge

The course aims to introduce the paradigms to neural networks and deep learning, including the basics of recurrent neural networks and models for complex data, model design and validation, and application to health problems and case studies

 

Modalità di verifica delle conoscenze

 The assessment of knowledge will be the subject of the written and project exam evaluation.

 

Assessment criteria of knowledge

 The assessment of knowledge will be the subject of the written and project exam evaluation.

 

Capacità

The student who completes the course successfully will be able to Identify problems facing healthcare providers that machine learning can solve and analyze how AI affects patient care safety, quality, and research.

 

 

Skills

The student who completes the course successfully will be able to Identify problems facing healthcare providers that machine learning can solve and analyze how AI affects patient care safety, quality, and research.

 

Modalità di verifica delle capacità

The student will have to solve a deep learning problem during a practical test.

   

Assessment criteria of skills

The student will have to solve a deep learning problem during a practical test.

   

Comportamenti

The student will acquire a method to deal with deep learning problems and to select the most effective solution to be adopted

   

Behaviors

The student will acquire a method to deal with deep learning problems and to select the most effective solution to be adopted

   

Modalità di verifica dei comportamenti

During the lab sessions, the accuracy and precision of the activities carried out will be evaluated

 

 

Assessment criteria of behaviors

During the lab sessions, the accuracy and precision of the activities carried out will be evaluated

 

Prerequisiti (conoscenze iniziali)

Basic knowledge of mathematics

Knowledge of programming in python

Knowledge of the various machine learning techniques presented in the Artificial Intelligence I course

 

Lo studente è invitato a verificare l'esistenza di eventuali propedeuticità consultando il Regolamento del Corso di studi relativo al proprio anno di immatricolazione. Un esame sostenuto in violazione delle regole di propedeuticità è nullo (Regolamento didattico d’Ateneo, art. 24, comma 3)" (Regolamento didattico d’Ateneo, art. 24, comma 3)

 

Prerequisites

Basic knowledge of mathematics

Knowledge of programming in python

Programma (contenuti dell'insegnamento)

Syllabus:

  • Health data
  • DNN
  • Embedding
  • CNN
  • RNN
  • Autoencoder
  • Attention models
  • Graph neural network
  • Memory network
  • Deep generative model
Syllabus

Syllabus:

  • Health data
  • DNN
  • Embedding
  • CNN
  • RNN
  • Autoencoder
  • Attention models
  • Graph neural network
  • Memory network
  • Deep generative model
Bibliografia e materiale didattico

Recommended book: Introduction to Deep Learning for Healthcare, Cao Xiao  Jimeng Sun

Papers on different algorithms described during the course

Slides of the lectures

Code written during the exercises

 

 

Bibliography

Recommended book: Introduction to Deep Learning for Healthcare, Cao Xiao  Jimeng Sun

Papers on different algorithms described during the course

Slides of the lectures

Code written during the exercises

 

Modalità d'esame

Written test plus individual project and oral exam

 

 

Assessment methods

Written test plus individual project and oral exam

Updated: 12/02/2024 11:27