Obtenha acesso a este curso exclusivo e a mais de 2600 horas de aprendizado com o

...por ano

O que está incluído em

Este curso online exclusivo

Detalhes

4 aulas (1h 32m)

1 CE Credits

inglês

Acesso à gravação durante o período de Premium

The technical foundation of AI in dentistry: what AI, machine learning, and deep learning are, how models learn from data, and how they generate clinical outputs.

This course is designed for dentists who want to unlock the “closed doors” of AI and understand what really happens behind the technology they increasingly encounter in clinical practice. Instead of treating AI as a black box, the course provides a clear, practical foundation for understanding how AI systems work, how they learn, and how their outputs should be interpreted.

During the course, you will learn about:

– The relationship between artificial intelligence, machine learning, and deep learning
– Supervised, unsupervised, and reinforcement learning
– Training data, validation, and the impact of data quality on AI reliability
– Programming and algorithms explained without technical coding
– The black box problem and the limitations of AI explainability
– Classification, detection, and segmentation in dental AI
– Generative AI and large language models compared with diagnostic AI
– Sensitivity, specificity, PPV, and NPV for evaluating AI performance
– How to critically assess AI tools, research findings, and marketing claims.

By the end of the course, you will have a practical understanding of what happens behind dental AI, how AI generates clinical outputs, and how to evaluate its capabilities and limitations with greater confidence.

Aula 1.AI, Machine Learning, and Deep Learning

– The difference between AI, machine learning, and deep learning
– A simple nested model: AI as the broad goal, machine learning as one approach, and deep learning as one type of machine learning
– Narrow AI, general AI, and superintelligent AI: why current dental AI tools are narrow AI
– Rule-based software of the 1990s and 2000s versus learning-based software today.

Aula 2.How Models Learn: Training and the Three Learning Types

– Training data, labels, and validation sets using a caries detection example
– Supervised learning with labeled radiographs
– Unsupervised learning for identifying hidden groupings without labels
– Reinforcement learning through trial and error and reward
– How training on 50 radiographs differs from training on 50,000
– Garbage in, garbage out: how mislabeled or narrow training data produces flawed models.

Aula 3.Generative AI and Large Language Models

– How generative AI (Claude, ChatGPT) differs from diagnostic AI: producing new content versus identifying a finding
– Autoregressive next-word prediction explained in plain language
– Live demo: a general-purpose AI assistant answering a clinical question and discussing what it is and is not doing
– Where generative AI fits in dentistry today: patient communication and education, not diagnosis.

Aula 4.What Programming Is, and the Black Box Problem

– What a computer program and an algorithm are, without writing code
– Why deep learning models often cannot explain their reasoning in clinically meaningful terms
– Explainable AI (XAI): heat maps and saliency maps, and what they do and do not prove.

O curso inclui aulas: