Machine Learning Tutorial
The Symposium includes an advanced machine learning tutorial, aimed primarily at local students and young researchers. It will take place on Friday, October 25, 2019, during the afternoon.
• Topic: Neural Network optimisation
Modern neural network architecture reflects the complexity of the problem. So those may become quite complex and computationally heavy. Usually, there are plenty of different meta-parameters to tune: number of layers, activation function, number of neurons per layer, drop-out rate, etc. There many different methods and tools that aimed at tuning those parameters for various reasons - accuracy, memory footprint or inference rate. This mini-course will cover the basics approaches for neural networks optimizing including hyperparameter optimization, network architecture search and Bayesian Neural Network perspective. Practical hands-on sessions will follow the theoretical introduction
• Expected knowledge for you to take this tutorial
- Python, Numpy, Pytorch
- The most fundamental ideas behind neural networks building blocks: regular, convolutional, drop-out and normalisation layers. You Should have tried to design several networks by yourself.
To register for the tutorial, you have to register for the event in the Indico page for AISIS 2019 and select the registration for the tutorial. If you already registered, you can modify your registration to select participation in the tutorial.