Lessons
Contents
Lessons#
1. Model#
1. solving regression problem with ML
2. solving classification problem with ML
3. neural networks for regression
4. neural network for classification
6. building neural network with PyTorch
7. training pytorch based models
2. Hyperparameter optimization#
1. hyperparameter optimization using Model class
2. hyperparameter optimizing using HyperOpt class
3. Model comparison#
1. compare ml models for regression
2. compare ml models for classification
4. preprocessing#
5. post-processing#
1. postprocessing of regression results
2. postprocessing of classification results
4. visualizing neural networks
5. interpretable machine learning
6. interpretable deep learning
7. model agnostic interpretaion methods
6. Avanced topics#
3. multi-output neural network
7. Autoencoders and variational autoencoders
9. customizing training loop in tensorflow
10. customizing training loop in pytorch
11. customizing loss function in tensorflow
12. customizing loss function in pytorch