COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |

University of Cambridge > Talks.cam > Isaac Newton Institute Seminar Series > Statistical theory for deep neural networks with ReLU activation function

## Statistical theory for deep neural networks with ReLU activation functionAdd to your list(s) Download to your calendar using vCal - Johannes Schmidt-hieber (Universiteit Leiden)
- Wednesday 21 March 2018, 11:30-12:30
- Seminar Room 1, Newton Institute.
If you have a question about this talk, please contact info@newton.ac.uk. STSW02 - Statistics of geometric features and new data types The universal approximation theorem states that neural networks are capable of approximating any continuous function up to a small error that depends on the size of the network. The expressive power of a network does, however, not guarantee that deep networks perform well on data. For that, control of the statistical estimation risk is needed. In the talk, we derive statistical theory for fitting deep neural networks to data generated from the multivariate nonparametric regression model. It is shown that estimators based on sparsely connected deep neural networks with ReLU activation function and properly chosen network architecture achieve the minimax rates of convergence (up to logarithmic factors) under a general composition assumption on the regression function. The framework includes many well-studied structural constraints such as (generalized) additive models. While there is a lot of flexibility in the network architecture, the tuning parameter is the sparsity of the n etwork. Specifically, we consider large networks with number of potential parameters being much bigger than the sample size. Interestingly, the depth (number of layers) of the neural network architectures plays an important role and our theory suggests that scaling the network depth with the logarithm of the sample size is natural. - https://arxiv.org/abs/1708.06633 – Article
This talk is part of the Isaac Newton Institute Seminar Series series. ## This talk is included in these lists:- All CMS events
- Featured lists
- INI info aggregator
- Isaac Newton Institute Seminar Series
- School of Physical Sciences
- Seminar Room 1, Newton Institute
Note that ex-directory lists are not shown. |
## Other listsCambridge Public Policy Lecture Series Darwin Humanities and Social Sciences Seminar Cambridge University Global Health Student Initiative - Seminar Series## Other talksSupporting Innovation in Quantum Technologies My VM is Lighter (and Safer) than your Container Modelling mitochondrial dysfunction in Parkinsonâ€™s disease: mitophagy, calcium and beyond Stochastic gradient & Random coordinate descent methods - Part 2 Breast cancer - demographics, presentation, diagnosis and patient pathway Beating your final boss battle, or presenting with confidence and style (tough mode) |