Neural and Behavioral Modeling @ NTU, given by Prof. Tsung-Ren Huang.
| Week | Subject |
|---|---|
| 01 | National Holiday |
| 02 | Course Introduction: Models & modeling |
| 03 | Behavioral Modeling (1/2): System dynamics |
| 04 | Behavioral Modeling (2/2): Agent-based modeling |
| 05 | Computational Cognitive Science (1/2): Basics |
| 06 | National Holiday |
| 07 | Computational Cognitive Science (2/2): Advanced |
| 08 | Computational Cognitive Neuroscience (1/8): Modeling principles & canonical neural computation |
| 09 | Computational Cognitive Neuroscience (2/8): Overview of learning & memory |
| 10 | Computational Cognitive Neuroscience (3/8): Local/shallow learning & memory |
| 11 | Computational Cognitive Neuroscience (4/8): Global/deep learning & memory |
| 12 | Computational Cognitive Neuroscience (5/8): Deep convolutional neural networks |
| 13 | Computational Cognitive Neuroscience (6/8): Deep reinforcement learning |
| 14 | Computational Cognitive Neuroscience (7/8): Deep recurrent neural networks |
| 15 | Computational Cognitive Neuroscience (8/8): Advanced issues & models |
| 16 | Computational Neuroscience (1/2): 1 spiking neuron |
| 17 | Computational Neuroscience (2/2): N spiking neurons |
| # | Description |
|---|---|
| 01 | no assignment |
| 02 | 1. Party Simulation 2. Shunting Equation |
| 03 | 1. Nonlinear love triangle 2. Tragedy of the Commons |
| 04 | Replicate one Agent-Based Model (group genesis in homogeneous population) |
| 05 | 1. Drifit Diffusion Model 2. Port EZdata.m from Matlab to Python |
| 08 | Replicate Sequence Memory Model |
| 09 | no assignment |
| 10 | 2-layered Linear Network(numpy & pytorch version) |
| 11 | Tuning the performance of a neural net |
| 12 | 1. Neural Network performance assessment 2. Universal Approximation Theorem |
| 14 | Activation/Signal Function in RNN |
| 15 | 1. Visualizing the latent space of an autoencoder 2. Integer Factorization |
| 16 | Integrate-and-Fire Neuron with a Refractory Period |
| 17 | (optional) |