Search for tag: "trial"

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 21 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  

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 48 views 0  

Bill Moggridge - It's getting so complicated

Bill Moggridge is the co-founder of IDEO, an internationally recognized design firm. He has designed the first laptop computer, the GRiD Compass, and pioneered Interaction Design as a discipline.…

From  Kathryn Gentilello 5 Months ago 3 views 0  

Michael Mitzenmacher - Bloom Filters, Cuckoo Hashing, Cuckoo Filters, Adaptive Cuckoo Filters, and Learned Bloom Filters

I will go over some of my past and present work on hashing-based data structures. After presenting some background on Bloom filters and cuckoo hashing, we will describe cuckoo filters, an efficient…

From  Kathryn Gentilello 5 Months ago 25 views 0  

Gabor Lugosi - Mean Estimation: Median-of-Means Tournaments

In these lectures we discuss some statistical problems with an interesting combinatorial structure behind. We start by reviewing the "hidden clique" problem, a simple prototypical example…

From  Kathryn Gentilello 6 Months ago 14 views 0  

Gabor Lugosi - Combinatorial Testing Problems

In these lectures we discuss some statistical problems with an interesting combinatorial structure behind. We start by reviewing the "hidden clique" problem, a simple prototypical example…

From  Kathryn Gentilello 6 Months ago 23 views 0  

Mary Wootters - Improved Decoding of Folded Reed-Solomon and Multiplicity Codes

List-decoding is an important primitive in the theory of error correcting codes, and it has long been a goal to obtain explicit constructions of capacity-achieving, efficiently list-decodable codes. …

From  Kathryn Gentilello 7 Months ago 17 views 0  

Sara van de Geer - The Debiased Lasso

In the third lecture we use sparsity to establish confidence intervals for a parameter of interest. The idea is to use the penalized estimator as an initial estimator in a one-step Newton-Raphson…

From  Kathryn Gentilello 8 Months ago 86 views 0  

Sara van de Geer - Compatibility and the Lasso

We will see in the first lecture that one needs conditions which relate the penalty to the risk function. They have in a certain sense to be “compatible”. We discuss these compatibility…

From  Kathryn Gentilello 8 Months ago 63 views 0  

Sara van de Geer - Sharp Oracle Inequalities for Non-Convex Loss

There will be three lectures, which in principle will be independent units. Their common theme is exploiting sparsity in high-dimensional statistics. Sparsity means that the statistical model…

From  Kathryn Gentilello 8 Months ago 105 views 0  

Ordered and disordered motion in dense active materials - Ludovic Berthier

We discuss how the non-equilibrium driving forces introduced by the natural biological activity or by physical self-propulsion mechanisms generically affect the structure, dynamics and phase behavior…

From  Kathryn Gentilello A year ago 40 views 0  

Local and global avalanches in sheared granular materials - Aghil Abed Zadeh

We perform a stick-slip experiment to characterize avalanches for granular materials. In our experiment, a constant speed stage pulls a slider which rests on a vertical bed of circular photoelastic…

From  Kathryn Gentilello A year ago 24 views 0  

Exploiting disorder - Sid Nagel

We are taught to understand solids by considering ideal crystals. This approach becomes untenable as the amount of disorder increases; for a glass with no well-defined long-range order, a crystal is…

From  Kathryn Gentilello A year ago 12 views 0