|
Week - 1 |
Introduction to Artificial Neural Networks: Perceptrons, Neurons, Weights and Biases |
|
Week - 2 |
Artificial Neural Networks – Activation & Evaluation: Activation Functions, Training vs Testing |
|
Week - 3 |
Artificial Neural Networks – Training Fundamentals: Feed-forward, Backpropagation, Stochastic Gradient Descent, Loss Functions |
|
Week - 4 |
Artificial Neural Networks – Regularization & Metrics: Regularization Techniques, Performance Evaluation Measures |
|
Week - 5 |
Introduction to Deep Neural Networks: Deep Architectures, Network Layers, Learning Rates, Feed-forward and Backpropagation in Deep Nets |
|
Week - 6 |
Deep Neural Networks – Hyper parameters & Optimization: Hyper parameters, Optimization Algorithms, Regularization, Dropout |
|
Week - 7 |
Midterm exam |
|
Week - 8 |
CNNs – Architectures & Applications: Well-known CNN Architectures (e.g., LeNet, AlexNet, VGG), Sample Applications |
|
Week - 9 |
CNNs – Technical Details: CNN Layers, Convolutions, Subsampling, Backpropagation in CNNs |
|
Week - 10 |
RNNs – Basics: Time Series Data, RNN Structure, Backpropagation Through Time (BPTT), Training and Testing |
|
Week - 11 |
RNNs – Architectures: Well-known RNN Architectures (LSTM, GRU) |
|
Week - 12 |
RNNs – Applications: Sequence Modeling Applications (e.g., NLP, Forecasting), Sample Projects |
|
Week - 13 |
Introduction to Reinforcement Learning: Agent-Environment Loop, MDPs, Exploration vs Exploitation, Rewards, Policy, Value Function |
|
Week - 14 |
Final Exam |
Eskisehir Technical University Info Package