Conveners
Machine Learning
- Lukas Heinrich (echnical University Munich)
Machine Learning
- Anindita Maiti (Perimeter Institute)
Machine Learning
- Michael A. Kagan (SLAC)
Machine Learning
- Minho SON (Korea Advanced Institute of Science and Technology)
Nonparametric methods, such as nearest neighbor and kernel methods, can offer simple and parallelizable algorithms without the need for manual structure tunning. However, these methods may suffer from severe performance degradation due to biases from the high-dimensionality of data. I will introduce recently derived equations for understanding and addressing the high-dimensional bias and...
Neural Networks (NN), the backbones of Deep Learning, define field theories through output ensembles at initialization. Certain limits of NN architecture give rise to free field theories via Central Limit Theorem (CLT), whereas other regimes give rise to weakly coupled, and non-perturbative field theories, via small, and large deviations from CLT, respectively. I will present a systematic...
