notes for Advanced Machine Learning course
- machine learning fundamentals
- decision trees
- deep neural networks
- convolutional neural networks
- computer vision meets deep learning: part1, part2
- recurrent neural networks and attention
- autoencoders and GANs
- Handwritten digits classification using MNIST dataset with Pytorch
- models: perceptron, deep fully-connected network, generic CNN
- various activations,
- overfitting,
- regularization, early stopping
- ECG signal classification
- classifiers comparison: SVM, decision trees, random forests
- feature vectors
- Image classification using deep CNNs
- VGG, ResNet
- Augmentation in image processing, two separated tasks:
- take MNIST or CIFAR dataset, apply some simple geometric transformations (see e.g. lecture), and check if such dataset extending improves accuracy (take some CNN model from previous labs)
- play with one-shot style transfer, understand the idea and run some exemplary code