37 citations · 114 across the 11 of their papers we have counts for
12 papers
Quantum Orthogonal Separable Physics-Informed Neural Networks
Pietro Zanotta, Ljubomir Budinski, Caglar Aytekin +1
This paper introduces Quantum Orthogonal Separable Physics-Informed Neural Networks (QO-SPINNs), a novel architecture for solving Partial Differential Equations, integrating quantu…
LEURN: Learning Explainable Univariate Rules with Neural Networks
Caglar Aytekin
In this paper, we propose LEURN: a neural network architecture that learns univariate decision rules. LEURN is a white-box algorithm that results into univariate trees and makes ex…
Neural Networks are Decision Trees
Caglar Aytekin
In this manuscript, we show that any neural network with any activation function can be represented as a decision tree. The representation is equivalence and not an approximation,…
A Sub-band Approach to Deep Denoising Wavelet Networks and a Frequency-adaptive Loss for Perceptual Quality
Caglar Aytekin, Sakari Alenius, Dmytro Paliy +1
In this paper, we propose two contributions to neural network based denoising. First, we propose applying separate convolutional layers to each sub-band of discrete wavelet transfo…
Compressing Weight-updates for Image Artifacts Removal Neural Networks
Yat Hong Lam, Alireza Zare, Caglar Aytekin +4
In this paper, we present a novel approach for fine-tuning a decoder-side neural network in the context of image compression, such that the weight-updates are better compressible.…
A Compression Objective and a Cycle Loss for Neural Image Compression
Caglar Aytekin, Francesco Cricri, Antti Hallapuro +3
In this manuscript we propose two objective terms for neural image compression: a compression objective and a cycle loss. These terms are applied on the encoder output of an autoen…
Compressibility Loss for Neural Network Weights
Caglar Aytekin, Francesco Cricri, Emre Aksu
In this paper we apply a compressibility loss that enables learning highly compressible neural network weights. The loss was previously proposed as a measure of negated sparsity of…
Block-optimized Variable Bit Rate Neural Image Compression
Caglar Aytekin, Xingyang Ni, Francesco Cricri +3
In this work, we propose an end-to-end block-based auto-encoder system for image compression. We introduce novel contributions to neural-network based image compression, mainly in…
A Theoretical Investigation of Graph Degree as an Unsupervised Normality Measure
Caglar Aytekin, Francesco Cricri, Lixin Fan +1
For a graph representation of a dataset, a straightforward normality measure for a sample can be its graph degree. Considering a weighted graph, degree of a sample is the sum of th…
Clustering and Unsupervised Anomaly Detection with L2 Normalized Deep Auto-Encoder Representations
Caglar Aytekin, Xingyang Ni, Francesco Cricri +1
Clustering is essential to many tasks in pattern recognition and computer vision. With the advent of deep learning, there is an increasing interest in learning deep unsupervised re…
Memory-Efficient Deep Salient Object Segmentation Networks on Gridized Superpixels
Caglar Aytekin, Xingyang Ni, Francesco Cricri +2
Computer vision algorithms with pixel-wise labeling tasks, such as semantic segmentation and salient object detection, have gone through a significant accuracy increase with the in…
INTEL-TUT Dataset for Camera Invariant Color Constancy Research
Caglar Aytekin, Jarno Nikkanen, Moncef Gabbouj
In this paper, we provide a novel dataset designed for camera invariant color constancy research. Camera invariance corresponds to the robustness of an algorithm's performance when…