Dániel Terbe

AI Researcher & Developer


Experience

October 2020 - January 2021
University of Szeged (SZTE) Logo

Self-Employed AI Consultant – University of Szeged (SZTE)

Department of Computer Algorithms and Artificial Intelligence, Szeged, Hungary

Involved in a project aimed at improving impaired speech using deep learning tools. The main focus was on leveraging Generative Adversarial Networks (GANs) and exploring transformer-based voice conversion models to enhance the speech quality of dysarthric patients.

August 2017 - Present
Institute for Computer Science and Control (SZTAKI) Logo

Developer & Researcher – Institute for Computer Science and Control

(HUN-REN SZTAKI) Optical Sensing and Processing Laboratory, Budapest, HUN

During my MSc studies, I began working here part-time on a project to detect subtle skin color changes related to the cardiac cycle using regular cameras, enabling remote pulse-rate measurement. This work became the foundation of my MSc thesis. After graduating, I transitioned to a full-time role and joined the digital holography project in 2020 – where I am responsible for the AI-related tasks. This project eventually led to the founding of a startup, HoloDetect. Learn more at: holodetect.com.

March 2016 - June 2016
Turbine Ltd. Logo

Research Intern – Turbine

turbine.ai, Budapest, Hungary

Turbine’s goal is to design effective and personalised cancer combination therapies using artificial intelligence and computer simulations. My task was to explore machine learning (deep learning) applications in the field of computational biology.

September 2015 - January 2020
Institute of Experimental Medicine (KOKI) Logo

Student Researcher – Institute of Experimental Medicine

(HUN-REN KOKI) Computational Neuroscience Workgroup, Budapest, Hungary

I've started working in this role during my BSc studies, focusing on the statistical inference of realistic neuron model parameters through computer simulations and Bayesian statistical tools. This work formed the basis of my BSc thesis and continued for several years after my graduation.

Education

January 2025 - Present
World Quant University Logo

MSc in Financial Engineering

World Quant University, New Orleans, USA

Capstone Project: ...

2017 - 2021
Pázmány Péter Catholic University Logo

MSc in Info-Bionics Engineering

Pázmány Péter Catholic University, Budapest, Hungary

Specialization: Bionic Interfaces and Integrated Structures.
Thesis: Remote camera-based pulse estimation using deep learning tools.

2013 - 2017
Eötvös Loránd University Logo

BSc in Physics

Eötvös Loránd University, Budapest, Hungary

Specialization: Theoretical Physics.
Thesis: Estimating the biophysical parameters of neurons using computer simulations and probabilistic models.

Publications

January 2024
Noise Background

Hologram Noise Model for Data Augmentation and Deep Learning

Terbe, D.; Orzó, L.; Bicsák, B.; Zarándy, Á.

Sensors 2024, 24, 948. DOI: https://doi.org/10.3390/s24030948

October 2022

Classification of Holograms with 3D-CNN

Terbe, D.; Orzó, L.; Zarándy, Á.

Sensors 2022, 22, 8366. DOI: https://doi.org/10.3390/s22218366

October 2021

Deep-learning-based bright-field image generation from a single hologram using an unpaired dataset

Terbe, D.; László, O.; Zarándy, Á.

Optics Letters 46.22 (2021): 5567-5570. DOI: https://doi.org/10.1364/OL.440900

July 2021

Continuous Camera-Based Premature-Infant Monitoring Algorithms for NICU

Nagy, Á.; Földesy, P.; Jánoki, I.; Terbe, D.; Siket, M.; Szabó, M.; Varga, J.; Zarándy, Á.

Applied Sciences. 2021; 11(16):7215. DOI: https://doi.org/10.3390/app11167215

Conferences

December 2022

Reliable estimation of neuronal biophysical parameters from electrophysiological recordings

D. Terbe, M. Szoboszlay, Z. Nusser, Sz. Káli

2022 Society for Neuroscience (SfN) Conference, San Diego, CA, USA

Link: https://bit.ly/sfn-presentation

January 2022

The application of voice conversion methods to improve the speech quality of dysarthric patients

D. Terbe, L. Tóth, L. Ivaskó

XVIII. Hungarian Conference on Computational Linguistics, Szeged, January 27-28, 2022 Link: https://acta.bibl.u-szeged.hu/75872/

October 2020

Multi-Level Optimization for Enabling Life Critical Visual Inspections of Infants in Resource Limited Environment

Á. Zarándy, P. Földesy, Á. Nagy, I. Jánoki, D. Terbe, M. Siket, M. Szabó, and J. Varga

2020 IEEE International Symposium on Circuits and Systems (ISCAS), Seville, Spain, pp. 1-5 DOI: 10.1109/ISCAS45731.2020.9181040

January 2019

Remote camera based heart rate estimation

D. Terbe, Á. Zarándy

Hungarian Association for Image Processing and Pattern Recognition, 12th National Conference (KÉPAF 2019), Debrecen, January 28-31, 2019

Link: https://eprints.sztaki.hu/9703/

August 2018

Remote camera based measurement of human vital signs

D. Terbe, Á. Zarándy

The 16th International Workshop on Cellular Nanoscale Networks and their Applications, Budapest, Hungary, August 28-30, 2018, pp. 1-5

Link: https://ieeexplore.ieee.org/document/8470476

Skills

Python

90%

C++

54%

Deep Learning

90%

PyTorch

90%

Frontend

6%

MLOps

74%

Financial ML

65%

Research

88%

Writing

85%

Presentation

60%