This is the symbol we use for model weights/parameters.
This is the symbol we use for model weights/parameters. It represents all values that are tunable by the learning algorithm.
The symbol \( \theta \) denotes the list of all model parameters which are tunable through the learning algorithm. This comes from the often high-dimensional parameter space \( \theta \in \htmlClass{sdt-0000000052}{\Theta} \)
Jaeger, H. (n.d.). Neural Networks (AI) (WBAI028-05) Lecture Notes BSc program in Artificial Intelligence. Retrieved April 23, 2024, from https://www.ai.rug.nl/minds/uploads/LN_NN_RUG.pdf