Introduction in artificial intelligence ITB-ENG

Content

  1. History, Present, Future of AI, and Basics of Python and Numpy (Asteroid Game - OOP)

  2. Matrix Transformations (Asteroid Game - Linear Algebra, OOP)

  3. Inverse Kinematics (Numpy, Advanced Mathematics, Partial Derivatives)

  4. Regression Tasks, Step-by-Step without OOP (Numpy)

  5. Regression Tasks, with OOP, Input Normalization (Numpy)

  6. Regression Tasks, Classification Tasks, Categorical Inputs (PyTorch)

  7. Image Classification, ConvNets (VGG, Kernel Function Implementation)

  8. Image Classification, ResNet, DenseNet

  9. Representation Learning, Anomaly Detection, AE, DAE, VAE

  10. Image Semantic Segmentation, UNet, YOLO

  11. Time Series Tasks, Recurrent Neural Networks, RNN, LSTM

  12. Time Series Attention/Transformer Models

  13. Image Classification with Attention/Transformer Models

  14. Reinforcement Learning, Q-Learning

  15. Reinforcement Learning, Gradient Policy

  16. Deep Metric Learning, Contrastive Loss, Triplet Loss

  17. Generative Models, DCGAN, WGAN

Course Evaluation

Points are awarded for each task! 

50% of the grade from homework 

50% final exam (in paper format)

Each session will include source code templates and a whiteboard link, where the board will be visible in real-time. Lectures will be held in real-time on a private YouTube Live channel, and questions can be asked in the comments.