Filters
Classification by Sparse Neural Networks
of computational units. Bounds on these norms are proven using the Chernoff–Hoeffding bound...
Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
- 2019 •
- Jimp •
- Link
Rok uplatnění
Jimp - Článek v periodiku v databázi Web of Science
Výsledek na webu
Probabilistic Lower Bounds for Approximation by Shallow Perceptron Networks
Limitations of approximation capabilities of shallow perceptron networks are investigated. Lower bounds on approximation errors are derived for binary-valued functions on a given domain. The results are obtained by combining probabilistic
Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
- 2017 •
- Jimp •
- Link
Rok uplatnění
Jimp - Článek v periodiku v databázi Web of Science
Výsledek na webu
Probabilistic Bounds on Complexity of Networks Computing Binary Classification Tasks
of computational units. Probabilistic lower bounds on these norms are derived using the Chernoff-Hoeffding Bound on sums of independent random variables, which need......
Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
- 2018 •
- D •
- Link
Rok uplatnění
D - Stať ve sborníku
Výsledek na webu
A tail bound for read-k families of functions
We prove a Chernoff-like large deviation bound on the sum of read-k non-independent random variables.
BA - Obecná matematika
- 2015 •
- Jx •
- Link
Rok uplatnění
Jx - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)
Výsledek na webu
Hoeffding and Bernstein Inequalities for U-statistics without Replacement
Concentration inequalities quantify random fluctuations of functions of random variables, typically by bounding the probability that such a function differs from its expected value by more than a certain amount. In this paper, we extend ...
Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
- 2022 •
- Jimp •
- Link
Rok uplatnění
Jimp - Článek v periodiku v databázi Web of Science
Výsledek na webu
Hoeffding’s Inequality for Sums of Dependent Random Variables
is a sharp upper bound on the probability that their sum is significantly larger than their mean? In the case of independent random variables, a fundamental tool for bounding such probabilities is devised by Wassily Hoeffding
Pure mathematics
- 2017 •
- Jimp •
- Link
Rok uplatnění
Jimp - Článek v periodiku v databázi Web of Science
Výsledek na webu
Hoeffding-Serfling Inequality for U-Statistics Without Replacement
Concentration inequalities quantify random fluctuations of functions of random variables, typically by bounding the probability that such a function differs from its expected value by more than a certain amount. In this paper we study one pa...
Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
- 2022 •
- O •
- Link
Rok uplatnění
O - Ostatní výsledky
Výsledek na webu
Hoeffding-Serfling Inequality for U-Statistics Without Replacement
Concentration inequalities quantify random fluctuations of functions of random variables, typically by bounding the probability that such a function differs from its expected value by more than a certain amount. In this paper we study one pa...
Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
- 2023 •
- Jimp •
- Link
Rok uplatnění
Jimp - Článek v periodiku v databázi Web of Science
Výsledek na webu
Model Complexities of Shallow Networks Representing Highly Varying Functions
of variational norms combined with the probabilistic Chernoff Bound. It is shown that almostModel complexities of shallow (i.e., one-hidden-layer) networks representing highly varying multivariable {-1,1}{-1,1}-valued functions are...
IN - Informatika
- 2016 •
- Jx •
- Link
Rok uplatnění
Jx - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)
Výsledek na webu
Probabilistic Bounds for Binary Classification of Large Data Sets
A probabilistic model for classification of task relevance is investigated. Correlations between randomly-chosen functions and network input-output functions are estimated. Impact of large data sets is analyzed from the point of view of the concentra...
Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
- 2020 •
- D •
- Link
Rok uplatnění
D - Stať ve sborníku
Výsledek na webu
- 1 - 10 out of 10 601