Search for tag: "tin"

Johannes Schmidt-Hieber - Mathematics for Deep Neural Networks: Energy landscape and open problems (Lecture 5/5)

To derive a theory for gradient descent methods, it is important to have some understanding of the energy landscape. In this lecture, an overview of existing results is given. The second part of the…

From  Kathryn Gentilello A month ago 19 views 0  

Johannes Schmidt-Hieber - Mathematics for Deep Neural Networks: Statistical theory for deep ReLU networks (Lecture 4/5)

We outline the theory underlying the recent bounds on the estimation risk of deep ReLU networks. In the lecture, we discuss specific properties of the ReLU activation function that relate to skipping…

From  Kathryn Gentilello A month ago 13 views 0  

Cherie R. Kagan - Designer Colloidal Nanocrystal Materials for Electronic and Optical Applications

Semiconductor and plasmonic nanocrystals are known for their size and shape dependent photo-luminescence and localized surface plasmon resonances, respectively. In this talk, I will describe the use…

From  Kathryn Gentilello 2 Months ago 11 views 0  

Johannes Schmidt-Hieber - Mathematics for Deep Neural Networks: Advantages of Additional Layers (Lecture 3/5)

Why are deep networks better than shallow networks? We provide a survey of the existing ideas in the literature. In particular, we discuss localization of deep networks, functions that can be easily…

From  Kathryn Gentilello 2 Months ago 18 views 0  

Johannes Schmidt-Hieber - Mathematics for Deep Neural Networks : Theory for shallow networks (Lecture 2/5)

We start with the universal approximation theorem and discuss several proof strategies that provide some insights into functions that can be easily approximated by shallow networks. Based on this, a…

From  Kathryn Gentilello 2 Months ago 26 views 0  

Johannes Schmidt-Hieber - Mathematics for Deep Neural Networks (Lecture 1/5)

Lecture 1) Survey on neural network structures and deep learning There are many different types of neural networks that differ in complexity and the data types that can be processed. This lecture…

From  Kathryn Gentilello 2 Months ago 47 views 0  

Galyna Livshyts - A Tight Net with Respect to a Random Matrix Norm and Applications to Estimating Singular Values

In this talk we construct a net around the unit sphere with good properties. We show that with exponentially high probability, the value of |Ax| on the sphere can be approximated well using this net,…

From  Kathryn Gentilello 3 Months ago 6 views 0  

Tuo Zhao - Towards Understanding First Order Algorithms for Nonconvex Optimization in Machine Learning

Stochastic Gradient Descent-type (SGD) algorithms have been widely applied to many non-convex optimization problems in machine learning, e.g., training deep neural networks, variational Bayesian…

From  Kathryn Gentilello 3 Months ago 13 views 0  

Éva Tardos - Learning and Efficiency of Outcomes in Games

Selfish behavior can often lead to suboptimal outcome for all participants, a phenomenon illustrated by many classical examples in game theory. Over the last decade we have studied Nash equilibria…

From  Kathryn Gentilello 3 Months ago 18 views 0  

Extended Reality (XR) for Teaching and Learning - Blair MacIntyre, David Joyner, Didier Contis, Miroslav Malesevic, Noah Posner, Matthew Swarts

Extended reality (XR) refers to real-and-virtual combined environment, including virtual reality (VR), augmented reality (AR), and mixed reality (MR). This talk explores the potential uses for…

From  Kathryn Gentilello 3 Months ago 20 views 0  

Howard Kushner - The Emergence of Kawasaki Disease in India: Why History (of Medicine) Matters

Dr. Howard Kushner is the Nat C. Robertson Distinguished Professor of Science and Society at Emory University. An historian of medicine, Kushner holds a joint appointment in the Graduate Institute of…

From  Kathryn Gentilello 5 Months ago 2 views 0