11 citations · 19 across the 23 of their papers we have counts for
31 papers
Theoretical Guarantees for One-Shot Magnitude Pruning and Compute-Adaptive Early Exit
Erdem Koyuncu
We study compute reduction in neural networks through a unified partial versus full computation view, captured by one-shot magnitude pruning in the static regime and early exit in…
A Large Scale Open-Source Image and Video Dataset for Robust Wildfire Detection and Classification
Emadeldeen Hamdan, Yingyi Luo, B. Ugur Toreyin +4
Wildfire detection and monitoring are critical for mitigating fire spread and reducing environmental and infrastructural damage. In this work, we introduce GWFP (Global Wildfire Pr…
Toward Generalizable Deep Learning Based Peatland Fire Detection via Walsh Hadamard Transform and Domain Adaptation
Emadeldeen Hamdan, Ahmad Faiz Tharima, Mohd Zahirasri Mohd Tohir +4
Machine learning-based wildfire detection has advanced significantly using deep learning models trained on large wildfire image and video datasets. However, peatland fires exhibit…
Model-Distributed Inference for Large Language Models at the Edge
Davide Macario, Hulya Seferoglu, Erdem Koyuncu
We introduce Model-Distributed Inference for Large-Language Models (MDI-LLM), a novel framework designed to facilitate the deployment of state-of-the-art large-language models (LLM…
Distributed Tomographic Reconstruction with Quantization
Runxuan Miao, Selin Aslan, Erdem Koyuncu +1
Conventional tomographic reconstruction typically depends on centralized servers for both data storage and computation, leading to concerns about memory limitations and data privac…
Early-Exit meets Model-Distributed Inference at Edge Networks
Marco Colocrese, Erdem Koyuncu, Hulya Seferoglu
Distributed inference techniques can be broadly classified into data-distributed and model-distributed schemes. In data-distributed inference (DDI), each worker carries the entire…
Memorization Capacity of Neural Networks with Conditional Computation
Erdem Koyuncu
Many empirical studies have demonstrated the performance benefits of conditional computation in neural networks, including reduced inference time and power consumption. We study th…
Class Based Thresholding in Early Exit Semantic Segmentation Networks
Alperen Görmez, Erdem Koyuncu
We propose Class Based Thresholding (CBT) to reduce the computational cost of early exit semantic segmentation models while preserving the mean intersection over union (mIoU) perfo…
Pruning Early Exit Networks
Alperen Görmez, Erdem Koyuncu
Deep learning models that perform well often have high computational costs. In this paper, we combine two approaches that try to reduce the computational cost while keeping the mod…
Federated Momentum Contrastive Clustering
Runxuan Miao, Erdem Koyuncu
We present federated momentum contrastive clustering (FedMCC), a learning framework that can not only extract discriminative representations over distributed local data but also pe…
Multiplication-Avoiding Variant of Power Iteration with Applications
Hongyi Pan, Diaa Badawi, Runxuan Miao +2
Power iteration is a fundamental algorithm in data analysis. It extracts the eigenvector corresponding to the largest eigenvalue of a given matrix. Applications include ranking alg…
Robust Principal Component Analysis Using a Novel Kernel Related with the L1-Norm
Hongyi Pan, Diaa Badawi, Erdem Koyuncu +1
We consider a family of vector dot products that can be implemented using sign changes and addition operations only. The dot products are energy-efficient as they avoid the multipl…
ECM: Early Exit via Class Means for Efficient Supervised and Unsupervised Learning
Alperen Görmez, Venkat R. Dasari, Erdem Koyuncu
State-of-the-art neural networks with early exit mechanisms often need considerable amount of training and fine tuning to achieve good performance with low computational cost. We p…
Quantizing Multiple Sources to a Common Cluster Center: An Asymptotic Analysis
Erdem Koyuncu
We consider quantizing an -dimensional sample, which is obtained by concatenating vectors from datasets of -dimensional vectors, to a -dimensional cluster center. The…
Optimal UAV Deployment for Rate Maximization in IoT Networks
Maryam Shabanighazikelayeh, Erdem Koyuncu
We consider multiple unmanned aerial vehicles (UAVs) at a common altitude serving as data collectors to a network of IoT devices. First, using a probabilistic line of sight channel…
A Generalization of Principal Component Analysis
Samuele Battaglino, Erdem Koyuncu
Conventional principal component analysis (PCA) finds a principal vector that maximizes the sum of second powers of principal components. We consider a generalized PCA that aims at…
Robust and Computationally-Efficient Anomaly Detection using Powers-of-Two Networks
Usama Muneeb, Erdem Koyuncu, Yasaman Keshtkarjahromi +3
Robust and computationally efficient anomaly detection in videos is a problem in video surveillance systems. We propose a technique to increase robustness and reduce computational…
The Tradeoff Between Coverage and Computation in Wireless Networks
Erdem Koyuncu
We consider a distributed edge computing scenario consisting of several wireless nodes that are located over an area of interest. Specifically, some of the "master" nodes are taske…
Optimal Placement of UAVs for Minimum Outage Probability
Maryam Shabanighazikelayeh, Erdem Koyuncu
We consider multiple unmanned aerial vehicles (UAVs) serving a density of ground terminals (GTs) as base stations. The objective is to minimize the outage probability of GT-to-UAV…
Asynchronous Local Construction of Bounded-Degree Network Topologies Using Only Neighborhood Information
Erdem Koyuncu, Hamid Jafarkhani
We consider ad-hoc networks consisting of wireless nodes that are located on the plane. Any two given nodes are called neighbors if they are located within a certain distance (…
Interleaving Channel Estimation and Limited Feedback for Point-to-Point Systems with a Large Number of Transmit Antennas
Erdem Koyuncu, Xun Zou, Hamid Jafarkhani
We introduce and investigate the opportunities of multi-antenna communication schemes whose training and feedback stages are interleaved and mutually interacting. Specifically, unl…
Power-Efficient Deployment of UAVs as Relays
Erdem Koyuncu
Optimal deployment of unmanned aerial vehicles (UAVs) as communication relays is studied for fixed-rate variable-power systems. The considered setup is a set of ground transmitters…
Performance Gains of Optimal Antenna Deployment for Massive MIMO Systems
Erdem Koyuncu
We consider the uplink of a single-cell multi-user multiple-input multiple-output (MIMO) system with several single antenna transmitters/users and one base station with antenna…
Deployment and Trajectory Optimization of UAVs: A Quantization Theory Approach
Erdem Koyuncu, Maryam Shabanighazikelayeh, Hulya Seferoglu
Optimal deployment and movement of multiple unmanned aerial vehicles (UAVs) is studied. The considered scenario consists of several ground terminals (GTs) communicating with the UA…