Milan Dubljanin

Mr. Milan Dubljanin

Department of Informatics, University of Priština in Kosovska Mitrovica, Faculty of Sciences and Mathematics, Pristina, Prishtinë, Kosovo
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 January 2026 in Information
Verified
Journal Article
Open access
PDF file
Milan DubljaninMilan Dubljanin
Milan Dubljanin
Stefan PanicStefan Panic
Stefan Panic
MSMilan Savić
Milan Savić
Milan DejanovicMilan Dejanovic
Milan Dejanovic
OPOliver Popović
Oliver Popović
This work investigates the effectiveness of block transform coding (BTC) as a lightweight, training-free quantization strategy for compressing the weights of pretrained deep neural networks. The proposed method applies a rule-based block transform with variance and root mean square error (RMSE)-driven stopping criteria, enabling substantial reductions in bit precision while preserving the statistical structure of convolutional and fully connected layer weights. Unlike uniform 8-bit quantization, BTC dynamically adjusts bit usage across layers and achieves significantly lower distortion for the same compression budget. We evaluate BTC across many pretrained architectures and tabular benchmarks. Experimental results show that BTC consistently reduces storage to 4–7.7 bits per weight while maintaining accuracy within 2–3% of the 32-bit floating point (FP32) baseline. To further assess scalability and baseline strength, BTC is additionally evaluated on large-scale ImageNet models and compared against a calibrated percentile-based uniform post-training quantization method. The results show that BTC achieves a substantially lower effective bit-width while incurring only a modest accuracy reduction relative to calibration-aware 8-bit quantization, highlighting a favorable compression–accuracy trade-off. BTC also exhibits stable behavior across successive post-training quantization (PTQ) configurations, low quantization noise, and smooth RMSE trends, outperforming naïve uniform quantization under aggressive compression. These findings confirm that BTC provides a scalable, architecture-agnostic, and training-free quantization mechanism suitable for deployment in memory- and computing-constrained environments.

28 September 2021 in International Journal of Numerical Modelling: Electronic Networks, Devices and Fields
Verified
Journal Article
Closed access
PDF file
Milan DejanovicMilan Dejanovic
Milan Dejanovic
Milan DubljaninMilan Dubljanin
Milan Dubljanin
NKNatasa Kontrec
Natasa Kontrec
SPStefan Panic
Stefan Panic
Danijel DjosicDanijel Djosic
Danijel Djosic
MSMihajlo Stefanovic
Mihajlo Stefanovic

1 January 2025
Verified
Conference Paper
Open access
PDF file
Milan DubljaninMilan Dubljanin
Milan Dubljanin
MSMilan Savić
Milan Savić
Milan DejanovicMilan Dejanovic
Milan Dejanovic
Artificial intelligence is the fastest-growing field of computer science. Its use is growing and yet to be fully uncovered. Using deep learning and datasets of specific data, artificial neural networks can be trained to help users in everyday life. This paper aims to make neural networks to help get the best time in a half marathon and marathons. Many factors influence marathon race times, such as temperature, precipitation, sunshine or atmospheric pressure, sex, age and physical preparation and current condition of runners. A dataset from smartwatches will be used to determine the condition of runners, as well as a dataset Berlin marathon dataset. Combining the analysis of these two datasets, neural networks will predict if the ideal time was achieved.

29 June 2026 in Algorithms
Verified
Journal Article
Open access
PDF file
Stefan PanicStefan Panic
Stefan Panic
Milan DubljaninMilan Dubljanin
Milan Dubljanin
MSMilan Savić
Milan Savić
MSMarko Smilić
Marko Smilić
This paper introduces an adaptive A-semilogarithmic gradient quantization framework aimed at reducing memory overhead and computational complexity during the training of deep neural networks. The approach employs a semilogarithmic companding function parameterized by a dynamically adjusted scaling factor A, which evolves in response to the statistical properties of gradients throughout the training process. Two distinct quantization strategies are proposed and evaluated: The switching piecewise A-quantizer, which adaptively toggles between low-bit uniform and high-bit semilogarithmic quantization according to an exponentially weighted moving-average (EMA) estimate of gradient variance; and the hybrid A-quantizer, which statically partitions the gradient domain, applying uniform quantization in low-magnitude regions and semilogarithmic companding in high-magnitude regions. The proposed methods are empirically evaluated on both multilayer perceptron (MLP) and convolutional neural network (CNN) architectures using tabular and image-classification benchmarks, including DCCC, CIFAR-10, CIFAR-100, and ImageNet. Quantitative results demonstrate that both models achieve comparable classification accuracy to full-precision (FP32) baselines while significantly reducing gradient reconstruction error. Notably, the hybrid A-quantizer consistently yields better validation accuracy, reduced RMSE, and improved convergence behavior relative to its switching counterpart. These findings underscore the effectiveness of hybrid semilogarithmic quantization as a robust and efficient solution for training deep models in resource-constrained or bandwidth-limited environments, with strong potential for scalable deployment across diverse hardware platforms.