Zobrazeno 1 - 10
of 1 421
pro vyhledávání: '"Freivalds A"'
We introduce a method for manipulating objects in three-dimensional space using controlled fluid streams. To achieve this, we train a neural network controller in a differentiable simulation and evaluate it in a simulated environment consisting of an
Externí odkaz:
http://arxiv.org/abs/2404.18181
Integer factorization is a famous computational problem unknown whether being solvable in the polynomial time. With the rise of deep neural networks, it is interesting whether they can facilitate faster factorization. We present an approach to factor
Externí odkaz:
http://arxiv.org/abs/2309.05295
Autor:
Freivalds, Karlis, Kozlovics, Sergejs
Generating diverse solutions to the Boolean Satisfiability Problem (SAT) is a hard computational problem with practical applications for testing and functional verification of software and hardware designs. We explore the way to generate such solutio
Externí odkaz:
http://arxiv.org/abs/2212.00121
There has been a growing number of machine learning methods for approximately solving the travelling salesman problem. However, these methods often require solved instances for training or use complex reinforcement learning approaches that need a lar
Externí odkaz:
http://arxiv.org/abs/2207.13667
Recurrent neural networks have flourished in many areas. Consequently, we can see new RNN cells being developed continuously, usually by creating or using gates in a new, original way. But what if we told you that gates in RNNs are redundant? In this
Externí odkaz:
http://arxiv.org/abs/2108.00527
Autor:
Ozolins, Emils, Freivalds, Karlis, Draguns, Andis, Gaile, Eliza, Zakovskis, Ronalds, Kozlovics, Sergejs
Modern neural networks obtain information about the problem and calculate the output solely from the input values. We argue that it is not always optimal, and the network's performance can be significantly improved by augmenting it with a query mecha
Externí odkaz:
http://arxiv.org/abs/2106.07162
Convolutional neural networks have become the main tools for processing two-dimensional data. They work well for images, yet convolutions have a limited receptive field that prevents its applications to more complex 2D tasks. We propose a new neural
Externí odkaz:
http://arxiv.org/abs/2006.15892
Attention is a commonly used mechanism in sequence processing, but it is of O(n^2) complexity which prevents its application to long sequences. The recently introduced neural Shuffle-Exchange network offers a computation-efficient alternative, enabli
Externí odkaz:
http://arxiv.org/abs/2004.04662
A key requirement in sequence to sequence processing is the modeling of long range dependencies. To this end, a vast majority of the state-of-the-art models use attention mechanism which is of O($n^2$) complexity that leads to slow execution for long
Externí odkaz:
http://arxiv.org/abs/1907.07897
Autor:
Freivalds, Karlis, Glagolevs, Jans
Publikováno v:
Freivalds K., Glagolevs J. (2014) Graph Compact Orthogonal Layout Algorithm. In: Fouilhoux P., Gouveia L., Mahjoub A., Paschos V. (eds) Combinatorial Optimization. ISCO 2014. Lecture Notes in Computer Science, vol 8596. Springer, Cham
There exist many orthogonal graph drawing algorithms that minimize edge crossings or edge bends, however they produce unsatisfactory drawings in many practical cases. In this paper we present a grid-based algorithm for drawing orthogonal graphs with
Externí odkaz:
http://arxiv.org/abs/1807.09368