Výsledky vyhledávání

Report

Parameter Estimation of Long Memory Stochastic Processes with Deep Neural Networks

Autor: Csanády, Bálint, Nagy, Lóránt, Boros, Dániel, Ivkovic, Iván, Kovács, Dávid, Tóth-Lakits, Dalma, Márkus, László, Lukács, András

We present a purely deep neural network-based approach for estimating long memory parameters of time series models that incorporate the phenomenon of long-range dependence. Parameters, such as the Hurst exponent, are critical in characterizing the lo

Externí odkaz: http://arxiv.org/abs/2410.03776

Zobrazit plný text záznamu

Report

LlamBERT: Large-scale low-cost data annotation in NLP

Autor: Csanády, Bálint, Muzsai, Lajos, Vedres, Péter, Nádasdy, Zoltán, Lukács, András

Large Language Models (LLMs), such as GPT-4 and Llama 2, show remarkable proficiency in a wide range of natural language processing (NLP) tasks. Despite their effectiveness, the high costs associated with their use pose a challenge. We present LlamBE

Externí odkaz: http://arxiv.org/abs/2403.15938

Zobrazit plný text záznamu

Report

Deep learning the Hurst parameter of linear fractional processes and assessing its reliability

Autor: Boros, Dániel, Csanády, Bálint, Ivkovic, Iván, Nagy, Lóránt, Lukács, András, Márkus, László

This research explores the reliability of deep learning, specifically Long Short-Term Memory (LSTM) networks, for estimating the Hurst parameter in fractional stochastic processes. The study focuses on three types of processes: fractional Brownian mo

Externí odkaz: http://arxiv.org/abs/2401.01789

Zobrazit plný text záznamu

Report

Dilated Convolutional Neural Networks for Lightweight Diacritics Restoration

Autor: Csanády, Bálint, Lukács, András

Diacritics restoration has become a ubiquitous task in the Latin-alphabet-based English-dominated Internet language environment. In this paper, we describe a small footprint 1D dilated convolution-based approach which operates on a character-level. W

Externí odkaz: http://arxiv.org/abs/2201.06757

Zobrazit plný text záznamu