SEDS 482
Software Engineering and Data Science Primer II
An introduction to the basic concepts of data science. Data science consists of machine learning algorithms and mathematical models (Supervised vs. unsupervised learning, decision tree pruning, training and testing datasets), big data tools to convert unstructured data into a structured form, and business intelligence to support decision-making.
| Week | Topics |
|---|---|
| 1 | History of artificial neural networks and introduction |
| 2 | Image classification with linear methods – I |
| 3 | Image classification with linear methods – II |
| 4 | Backpropagation – I |
| 5 | Backpropagation – II |
| 6 | Training artificial neural networks I: data preprocessing, weight initialization and regularization, batch normalization and loss functions |
| 7 | Training artificial neural networks II: gradient checking, babysitting the training process, update methods, hyper-parameter optimization |
| 8 | Convolutional neural networks – I |
| 9 | Convolutional neural networks – II |
| 10 | Spatial localization and object detection with convolutional neural networks |
| 11 | Visualization and understanding of convolutional neural networks |
| 12 | Recurrent neural networks |
| 13 | Training convolutional networks in practice: Data augmentation, transfer learning |
| 14 | Deep neural network coding frameworks |
