Zoltán Ádám Milacski
Zoltán Ádám Milacski
ELTE Eötvös Loránd University
Verified email at caesar.elte.hu
Cited by
Cited by
Robust Detection of Anomalies via Sparse Methods
ZÁ Milacski, M Ludersdorfer, A Lorincz, P van der Smagt
22nd International Conference on Neural Information Processing, 2015
Towards reasoning based representations: Deep consistence seeking machine
A Lőrincz, M Csákvári, Á Fóthi, ZÁ Milacski, A Sárkány, Z Tősér
Cognitive Systems Research 47, 92-108, 2018
Columnar Machine: Fast estimation of structured sparse codes
A Lőrincz, ZA Milacski, B Pinter, AL Verő
Biologically Inspired Cognitive Architectures 15, 19-33, 2016
MADGAN: unsupervised medical anomaly detection GAN using multiple adjacent brain MRI slice reconstruction
C Han, L Rundo, K Murao, T Noguchi, Y Shimahara, ZÁ Milacski, ...
BMC bioinformatics 22 (2), 1-20, 2021
Iterative calibration method for microscopic road traffic simulators
T Tettamanti, ZÁ Milacski, A Lőrincz, I Varga
Periodica Polytechnica Transportation Engineering 43 (2), 87-91, 2015
Differentiable Unrolled Alternating Direction Method of Multipliers for OneNet
ZÁ Milacski, B Póczos, A Lőrincz
30th British Machine Vision Conference (BMVC), 2019
Estimating cartesian compression via deep learning
A Lőrincz, A Sárkány, ZA Milacski, Z Tősér
International Conference on Artificial General Intelligence, 294-304, 2016
Cost and risk sensitive decision making and control for highway overtaking maneuver
A Mihály, ZÁ Milacski, Z Tősér, A Lőrincz, T Tettamanti, I Varga
2015 International conference on models and technologies for intelligent …, 2015
GAN-based multiple adjacent brain MRI slice reconstruction for unsupervised Alzheimer’s disease diagnosis
C Han, L Rundo, K Murao, ZÁ Milacski, K Umemoto, E Sala, H Nakayama, ...
International Meeting on Computational Intelligence Methods for …, 2019
Group k-Sparse Temporal Convolutional Neural Networks: Unsupervised Pretraining for Video Classification
ZÁ Milacski, B Póczos, A Lőrincz
2019 International Joint Conference on Neural Networks (IJCNN), 2019
Declarative description: The meeting point of artificial intelligence deep neural networks and human intelligence
Z Milacski, K Faragó, A Fóthi, V Varga, A Lorincz
XAI 2018, Proceedings of the 2nd Workshop on Explainable Artificial …, 2018
Cognitive deep machine can train itself
A Lőrincz, M Csákvári, Á Fóthi, ZÁ Milacski, A Sárkány, Z Tősér
arXiv preprint arXiv:1612.00745, 2016
CNN‐based MRI regression using u‐net
C HAN, F GESSER, Z Milacski
Enhancing Crowdsourced Applications via Incorporated Practice Sessions.
KB Faragó, ZA Milacski, A Nemeth, A Lörincz
GamifIR@ ECIR, 41-43, 2015
VideoOneNet: Bidirectional Convolutional Recurrent OneNet with Trainable Data Steps for Video Processing
Z Milacski, B Poczos, A Lorincz
International Conference on Machine Learning, 6893-6904, 2020
Multi Object Tracking for Similar Instances: A Hybrid Architecture
Á Fóthi, KB Faragó, L Kopácsi, ZÁ Milacski, V Varga, A Lőrincz
International Conference on Neural Information Processing, 436-447, 2020
Facility location functions are deep submodular functions
K Bérczi, E Bérczi-Kovács, A Lőrincz, ZÁ Milacski
EGRESQP 2018 (04), 2018
Adversarial Perturbation Stability of the Layered Group Basis Pursuit
D Szeghy, ZA Milacski, A Fóthi, A Lorincz
def 1, 2, 0
A Layered Group Basis Pursuit támadásokkal szembeni stabilitásának vizsgálata
D Szeghy, ZÁ Milacski, Á Fóthi, A Lőrincz
Fast Estimation of the Kernel Group LASSO
ZA Milacski, ST Hy, B Pinter, A Lorincz
The system can't perform the operation now. Try again later.
Articles 1–20