Sumários

Reinforcement learning in Python

25 Novembro 2024, 18:30 • Helena Aidos

- Introduction to gymnasium library

- Implementation of value iteration algorithm

Reinforcement learning [1/2]

25 Novembro 2024, 16:30 • Helena Aidos

- Markov Decision processes

- Policy evaluation
- Value iteration
- Model-based Monte Carlo
- Model-free Monte Carlo

Deep learning in Python

19 Novembro 2024, 13:00 • Helena Aidos

- Image classification with a Convolutional Neural Network using data augmentation, dropout and batch normalization

Deep learning in Python

18 Novembro 2024, 18:30 • Helena Aidos

- Image classification with a Convolutional Neural Network using data augmentation, dropout and batch normalization

Introduction to deep learning

18 Novembro 2024, 16:30 • Helena Aidos

- Perceptron

- Multi-layer perceptron
- Activation functions
- Loss function
- Training neural networks: gradient descent algorithm
- Convolutional Neural Network