V. Ceperic

发表

Predictive and generative machine learning models for photonic crystals

M. Soljačić, S. Picek, J. Joannopoulos, 2020, Nanophotonics.

Area-efficient differential Gaussian circuit for dedicated hardware implementations of Gaussian function based machine learning algorithms

A. Barić, V. Ceperic, D. Vrtaric, 2013, Neurocomputing.

Black-Box Modelling of Mixed-Signal Integrated Circuits

V. Ceperic, 2010 .

Heuristic recurrent algorithms for photonic Ising machines

Miles R. Johnson, Li Jing, Yichen Shen, 2018, Nature Communications.

Sparse ε-tube support vector regression by active learning

G. Gielen, A. Barić, V. Ceperic, 2014 .

On-Chip Optical Convolutional Neural Networks pdf

Vladimir Ceperic, Marin Soljacic, Yichen Shen, 2018, ArXiv.

Short-term forecasting of natural gas prices using machine learning and feature selection algorithms

Vladimir Ceperic, Ervin Ceperic, Saša Žiković, 2017 .

A Strategy for Short-Term Load Forecasting by Support Vector Regression Machines

Vladimir Ceperic, Adrijan Baric, Ervin Ceperic, 2013, IEEE Transactions on Power Systems.

3D Cardiac Electrical Activity Model

Ratko Magjarević, Siniša Sovilj, Vladimir Ceperic, 2016 .

Photonic Recurrent Ising Sampler

Dirk Englund, Li Jing, Mihika Prabhu, 2018, 2019 Conference on Lasers and Electro-Optics (CLEO).

Integration of Neural Network-Based Symbolic Regression in Deep Learning for Scientific Discovery

Vladimir Ceperic, Li Jing, Marin Soljacic, 2019, IEEE Transactions on Neural Networks and Learning Systems.

Reducing Complexity of Echo State Networks with Sparse Linear Regression Algorithms

Vladimir Ceperic, Adrijan Baric, A. Barić, 2014, 2014 UKSim-AMSS 16th International Conference on Computer Modelling and Simulation.

Artificial neural network in modelling of voltage controlled oscillators with jitter

V. Ceperic, A. Baric, B. Pejcinovic, 2004, Proceedings of the 12th IEEE Mediterranean Electrotechnical Conference (IEEE Cat. No.04CH37521).

Recurrent sparse support vector regression machines trained by active learning in the time-domain

Georges G. E. Gielen, Vladimir Ceperic, Adrijan Baric, 2012, Expert Syst. Appl..

Modeling of analog circuits by using support vector regression machines

Vladimir Ceperic, Adrijan Baric, A. Barić, 2004, Proceedings of the 2004 11th IEEE International Conference on Electronics, Circuits and Systems, 2004. ICECS 2004..

Sparse ε\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\varepsilon $$\end{document}-tube support vector regression by

Georges G. E. Gielen, Vladimir Ceperic, Adrijan Baric, 2013, Soft Computing.

Sparse multikernel support vector regression machines trained by active learning

Georges G. E. Gielen, Vladimir Ceperic, Adrijan Baric, 2012, Expert Syst. Appl..

On-Chip Optical Convolutional Neural Networks

Cott, Yichen Shen, S. Skirlo, 2018, ArXiv.