| wk | Title | Topics | Quiz | Hand in deliverable | Géron (Ed3) | Bradski | |
|---|---|---|---|---|---|---|---|
| 36 | 1.1 | Basic principles & set-up | Introduction Course organization Why machine learning? Machine learning approaches Python, Numpy primer OpenCV tutorial |
1 | 20.1.1,20.1.2,20.1.5 | ||
| 37 | 1.2 | Assignment kick-off | Assignment introduction ML portfolio template How to start? Conditioned acquisition Data collection example script and sci-kitlearn Feature engineering Splitting, exploring data |
1 | 20.1.6,20.1.7 | ||
| 38 | 1.3 | Feature data exploration | Basic segmentation and feature extraction Splitting your data Exploratory data analysis Feature engineering Data preparation |
1 ML principles |
2.1 2.4 - 2.5 |
799-848 859-864 875-906 |
|
| 39 | 1.4 | Supervised Machine Learning | Classification k-nearest neighbors Support vector machines Decision trees Random forests Bagging and boosting Optimization |
3.1 -3.2 3.4 3.6 - 3.7 5.1 - 5.2 6.1 - 6.3 6.7 7.1 - 7.4 |
|||
| 40 | 1.5 | ML performance | Training a classifier Thinking about performance Hyperparameter tuning Visualizing a decision tree Confusion matrix Evaluating a classifier Log loss Learning curves |
2 Data |
Preliminary ML report, Ch. 1-3 | 3.3 3.5 |
864 |
| 41 | 1.6 | Unsupervised Machine Learning | Clustering K-means Expectation maximization Dimensionality reduction Principal component analysis |
Feedback on other groups' preliminary report | 8.1 - 8.4 9 |
||
| 42 | 1.7 | Regression | Linear regression Logistic Regression Lasso Regression Classification and regression |
3 ML performance |
4 | 786-792 | |
| 43 | Holiday | ||||||
| 44 | 1.8 | No class | |||||
| 45 | 1.9 | No class | resit 1,2,3 | Full ML report | |||
| 46 | 2.1 | Artifical Neural Network (ANN) | Machine learning vs deep learning Biological neuron Perceptron Multi-layer perceptron (MLP) Backpropagation Regression and classification MLP |
10 | 849-858 | ||
| 47 | 2.2 | Deep Neural Network (DNN) | Vanishing and exploding gradients Transfer learning Training optimization Learning rate scheduling Regularization Data augmentation |
Resit ML report | 11 (12,13) | ||
| 48 | 2.3 | Convolutional Neural Network (CNN) | Visual cortex CNN vs MLP Recap convolution Convolutional layer Pooling layer CNN architecture |
4 ANN |
14 | ||
| 49 | 2.4 | Advanced CNN | Object detection Object tracking Semantic segmentation Variational autoencoder Edge computing Transfer learning |
17 | |||
| 50 | 2.5 | Vision Transfomers | tbd | 5 CNN |
|||
| 51 | 2.6 | Mind and machine, Cognitive Science introduction |
Mental representations Visual perception Cognitive approach Mind as a web Artificial Intelligence |
||||
| 52 | Holiday | ||||||
| 1 | Holiday | ||||||
| 2 | 2.7 | Wrap-up | |||||
| 3 | 2.8 | No class | |||||
| 4 | 2.9 | No class | DL report | ||||
| 5 | 2.10 | No class | resit 4, 5 |