Search Results for author: Gil Shabat

Found 7 papers, 0 papers with code

DL-DDA -- Deep Learning based Dynamic Difficulty Adjustment with UX and Gameplay constraints

no code implementations6 Jun 2021 Dvir Ben Or, Michael Kolomenkin, Gil Shabat

Dynamic difficulty adjustment ($DDA$) is a process of automatically changing a game difficulty for the optimization of user experience.

Generalized Quantile Loss for Deep Neural Networks

no code implementations28 Dec 2020 Dvir Ben Or, Michael Kolomenkin, Gil Shabat

This note presents a simple way to add a count (or quantile) constraint to a regression neural net, such that given $n$ samples in the training set it guarantees that the prediction of $m<n$ samples will be larger than the actual value (the label).

Majority Voting and the Condorcet's Jury Theorem

no code implementations8 Feb 2020 Hanan Shteingart, Eran Marom, Igor Itkin, Gil Shabat, Michael Kolomenkin, Moshe Salhov, Liran Katzir

There is a striking relationship between a three hundred years old Political Science theorem named "Condorcet's jury theorem" (1785), which states that majorities are more likely to choose correctly when individual votes are often correct and independent, and a modern Machine Learning concept called "Strength of Weak Learnability" (1990), which describes a method for converting a weak learning algorithm into one that achieves arbitrarily high accuracy and stands in the basis of Ensemble Learning.

Ensemble Learning

Fast and Accurate Gaussian Kernel Ridge Regression Using Matrix Decompositions for Preconditioning

no code implementations25 May 2019 Gil Shabat, Era Choshen, Dvir Ben Or, Nadav Carmel

This paper presents a method for building a preconditioner for a kernel ridge regression problem, where the preconditioner is not only effective in its ability to reduce the condition number substantially, but also efficient in its application in terms of computational cost and memory consumption.

Randomized LU decomposition: An Algorithm for Dictionaries Construction

no code implementations17 Feb 2015 Aviv Rotbart, Gil Shabat, Yaniv Shmueli, Amir Averbuch

Such approach is harder to deceive and we show that only a few file fragments from a whole file are needed for a successful classification.

General Classification

Missing Entries Matrix Approximation and Completion

no code implementations27 Feb 2013 Gil Shabat, Yaniv Shmueli, Amir Averbuch

The approximation constraint can be any whose approximated solution is known for the full matrix.

Matrix Completion

Cannot find the paper you are looking for? You can Submit a new open access paper.