Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 12 of 12 for “"neural network quantization"”.
-
QUANTIZATION AND APPROXIMATION OF NEURAL NETWORKS
… specific focus on the theoretical properties of neural networks. The first part of this work addresses neural network quantization. Despite the widespread use of quantization as a primary method for compressing deep neural networks, a majority of existing approaches lack provable guarantees. By …
-
LightMARL : smart swarm coordination in urban spaces
… To improve computation, the framework utilizes neural network quantization, structured pruning, and knowledge distillation tailored for multi-agent policy optimization (MAPPO). These methods decrease model size and computational demands while maintaining essential coordination behaviors. To …
-
Understanding and improving numerical stability of deep learning algorithms
… their numerical stability. Third, we focus on neural network quantization, which we found to cause numerical stability issues. Specifically, we propose a new quantization algorithm that optimizes the trade-off between low-bit representation and loss of precision. Next, we focus on analyzing the …
-
An Analysis Framework for the Quantization-Aware Design of Efficient, Low-Power Convolutional Neural Networks
Deep convolutional neural network (CNN) algorithms have emerged as a powerful tool for many computer vision tasks such as image classification, object detection, and semantic segmentation. However, these algorithms are computationally expensive and difficult to adapt for resource constrained …
-
Energy-Efficient Convolutional Neural Network Accelerators for Edge Intelligence
… from automated personal assistants and social network filtering to self-driving cars and drug development. The growth in popularity of these algorithms has its root in the exponential increase of computing power available for their training consequent to the diffusion of GPUs. The achieved …
-
TwinDNN: A tale of two deep neural networks
Compression technologies for deep neural networks (DNNs), such as weight quantization, have been widely investigated to reduce the model size so that they can be implemented on hardware with strict resource restrictions. However, one major disadvantage of model compression is accuracy degradation. …
-
Adaptive model inference under computational resource constraints
Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2024-05-01
-
Accelerating Quantized DNNs with Dedicated Hardware Accelerators and RISC-V Processors Using Precision-Scalable Multipliers
L'abstract è presente nell'allegato / the abstract is in the attachment
-
Research and Design of Neural Processing Architectures Optimized for Embedded Applications
… Ergebnisse an, um das Architekturdesign von Neural Processing Units (NPUs) zu verbessern. Die Optimierung neuronaler Netzwerkmodelle begann mit der Quantisierung neuronaler Netzwerke mit einfacher Präzision und entwickelte sich zu gemischter Präzision. Die Entwicklung der NPU-Architektur …
-
Umělá inteligence na platrofmě nVIDIA Jetson
Cílem této bakalářské práce je vytvoření, naučení a implementace umělé neuronové sítě ve vestavném zařízení NVIDIA Jetson Nano. V první části práce je popsán současný stav implementace umělé inteligence ve vestavných zařízeních. Následující část popisuje nástroje pro vývoj umělých neuronových sítí …
-
Chytrá kamera pro sledování zájmových objektů
Naše diplomová práce se zaměřuje na systémy hlubokého učení s nízkou spotřebou pracující v reálném čase, které využívají kvantizované neuronové sítě. Konkrétně implementujeme vícestupňovou aplikaci počítačového vidění, která provádí detekci vozidel, detekci registračních značek a jejich …
-
Towards Securing Quantized Deep Learning
… becomes a prerequisite in this context. Quantization emerges as one of the most practical solutions for compressing models. Quantized models can be efficiently deployed on microcontroller-based Internet of Things (IoT) devices, and the quantization process can be executed post-training, …