Iskalni niz:
išči po
išči po
išči po
išči po
Vrsta gradiva:
Jezik:
Št. zadetkov: 6
Deep learning for compressive sensing
Alina Luminita Machidon, Veljko Pejović
Pregledni znanstveni članek
Oznake: nevronske mreže;globoko učenje;kompresijsko zaznavanje;vseprisotno računalništvo;neural networks;deep learning;compressive sensing;ubiquitous computing;
Compressive sensing (CS) is a mathematically elegant tool for reducing the sensor sampling rate, potentially bringing context-awareness to a wider range of devices. Nevertheless, practical issues with the sampling and reconstruction algorithms prevent further proliferation of CS in real world domain ...
Leto: 2023 Vir: Fakulteta za računalništvo in informatiko (UL FRI)
Adaptive data-driven subsampling for efficient neural network inference
Alina Luminita Machidon, Veljko Pejović
Izvirni znanstveni članek
Oznake: neenakomerno vzorčenje;kompresijsko zaznavanje;globoko učenje;klasifikacija EEG;prepoznavanje govora;klasifikacija slike;nonuniform sampling;compressive sensing;deep learning;EEG classifcation;speech recognition;image classifcation;
In this paper we present a novel data-driven subsampling method that can be seamlessly integrated into any neural network architecture to identify the most informative subset of samples within the original acquisition domain for a variety of tasks that rely on deep learning inference from sampled si ...
Leto: 2024 Vir: Fakulteta za računalništvo in informatiko (UL FRI)
Integrating control-theoretic predictive deep learning for resource-efficient computing systems
Alina Luminita Machidon, Veljko Pejović
Izvirni znanstveni članek
Oznake: nadzorni sistemi;napovedni nadzor modela;globoko učenje;učinkovitost virov;prilagodljivost kontekstu;približno računalništvo;control systems;model predictive control;deep learning;resource effciency;context adaptivity;approximate computing;
Deep learning (DL) powers numerous applications on ubiquitous edge devices, but its high resource demands pose a challenge. Approximate computing is often proposed to alleviate this, yet such calculation usually suffers from a fixed level of accuracy loss. We propose a novel control-theoretic approa ...
Leto: 2025 Vir: Fakulteta za računalništvo in informatiko (UL FRI)
Reinforcement learning for efficient UAV-based computer vision
Brin Colnar, Veljko Pejović, Alina Luminita Machidon
Magistrsko delo
Oznake: reinforcement learning;unmanned aerial vehicle;precision agriculture;computer vision;computer science;master's thesis;
Weed control in precision agriculture illustrates the broader challenge of optimizing operational efficiency in dynamic environments - a principle relevant to fields as diverse as financial markets and environmental monitoring. To effectively meet these diverse needs, we have developed a suite of ...
Leto: 2024 Vir: Fakulteta za računalništvo in informatiko (UL FRI)
Efficient object detection for crop monitoring in precision agriculture
Jaša Kerec, Octavian-Mihai Machidon, Alina Luminita Machidon
Magistrsko delo
Oznake: neural networks;precision agriculture;object detection;neural architecture search;computer science;master's thesis;
This thesis presents an automated approach to designing energy-efficient neural network architecture for wheat head detection in precision agriculture. By leveraging neural architecture search (NAS) on the YOLOv8n model, we developed optimized architecture tailored for deployment on edge devices suc ...
Leto: 2025 Vir: Fakulteta za računalništvo in informatiko (UL FRI)
SqueezeSlimU-Net
Alina Luminita Machidon, Andraž Krašovec, Veljko Pejović, Octavian-Mihai Machidon
Izvirni znanstveni članek
Oznake: prilagodljive nevronske mreže;računalniška učinkovitost;segmentacija slike;natančno poljedelstvo;vid brezpilotnega letala v realnem času;odkrivanje plevela;adaptive neural networks;computational effciency;image segmentation;precision agriculture;real-time unmanned aerial vehicle vision;UAV;weed detection;
The limited processing capacity of computing equipment that is usually mounted on unmanned aerial vehicles (UAVs) often prevents real-time execution of computer vision tasks, such as image segmentation. In this article, we introduce SqueezeSlimU-Net (SSU-Net), an adaptive and efficient deep learning ...
Leto: 2025 Vir: Fakulteta za računalništvo in informatiko (UL FRI)
Št. zadetkov: 6
Ključne besede:
Leto izdaje:
Avtorji:
Repozitorij:
Tipologija:
Jezik: