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 20 of 32 for “"Post Training Quantization"”.
-
Adaptive Post-Training Quantization for Language-Centric Foundation Models
… storage, memory, and inference costs, motivating post-training quantization (PTQ) for efficient deployment. However, architectural and modality-specific differences govern how quantization affects internal representations and downstream performance, motivating complementary quantization approaches …
-
Post-Training Quantization of Generative and Discriminative LSTM Text Classifiers: A Study of Calibration, Class Balance, and Robustness
… faces computational and memory constraints. Post Training Quantization (PTQ) reduces model size and compute costs without retraining, making it ideal for edge deployment. In this work, we present a comprehensive comparative study of generative and discriminative Long Short Term Memory …
-
Exploring Accumulated Gradient-Based Quantization and Compression for Deep Neural Networks
… In this thesis, we devise and explore three quantization methods (post-training, in-training and combined quantization) that quantize 32-bit floating-point weights and biases to lower bit width fixed-point parameters while also achieving significant pruning, leading to model compression. We …
-
A Geometrical Approach to Machine Learning: From Complexity Measures to Quantization
… show that 2sED correlates well with the training error. For Markovian models, we show how to efficiently approximate 2sED from below through a layer-wise iterative approach, which allows us to tackle deep learning models with a large number of parameters. Simulation results suggest that …
-
Efficient quantization techniques for Large Language Models
Quantization has emerged as a critical technique in optimizing neural networks for efficient deployment across various hardware platforms. As Large Language Models (LLMs), which contain billions of parameters, continue to grow, quantization significantly reduces computational requirements, memory …
-
An Exploration of U-Net-Based Cloud Segmentation in the Bayer Domain for Satellite Imagery
… model compression through structural pruning and quantization. Structural pruning is implemented by progressively reducing the network depth to assess the trade-off between model complexity and segmentation accuracy. For the quantization, both post-training quantization and quantization-aware …
-
Generalized Machine Learning Quantization Implementation for High Level Synthesis Targeting FPGAs
… acceleration options. FINN utilizes Brevitas, a quantization aware training library. Using Brevitas, I trained a particle tracking network and demonstrated equivalent accuracy at lower bit precision than post training quantization. As a cross organizational project, the hls4ml and FINN teams …
-
Optimization of Deep Neural Networks for Efficient Resource Utilization
… edge devices. This thesis explores quantization as a model compression technique to improve inference efficiency while minimizing accuracy loss. Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT) were applied to MobileNetV2 and ResNet50 for classification on the …
-
Audio Based Road Type Classification Using CNNs and AST: Development of Audio Based Road Type Classification Models with Focus on Convolutional Neural Networks and The Audio Spectrogram Transformer Model
… advantages in inference speed and memory usage. Post-training quantization was applied to all models using Qualcomm’s AI Hub to determine their viability for deployment on mobile or embedded-systems. The findings highlight the potential of this audio-based road type classification as a composite …
-
Po mokymo atliekamos kvantizacijos poveikis didelių kalbos modelių kodo generavimo kokybei ir efektyvumui /
This thesis examines the impact of post-training quantization (PTQ) on the quality and efficiency of code generation in large language models. The study analyses the Qwen/Qwen2.5Coder-7B-Instruct model and four of its GGUF-format variants: a control F16 model, a publicly available Q4_K_M model, and …
-
Hyperspectral Image Classification of Satellite Images Using Compressed Neural Networks
… aufwendig und komplex, sodass die verfügbaren Trainingdaten oft nicht groß genug sind (Fluch der Dimensionalität). Deshalb beschäftigt sich diese Arbeit mit Methoden zur Dimensionsreduktion und deren Auswirkung auf verschiedenen Ebenen. Auf der einen Seite gibt es Verfahren zur Merkmalsauswahl …
-
Towards Green AI: Evaluating Energy Efficiency for Quantized LLM Inference
While it is known that quantization of large language models (LLMs) reduces memory usage via lower-bit weights, studies quantifying the resulting impact on energy usage and carbon intensity are scarce. We present the first unified evaluation of weight-only quantization strategies for LLM inference …
-
Lightweight ML-Based Drone Intrusion Detection System through Model Compression
… a quantized deep neural network (DNN) through post-training quantization (PTQ), enabling real-time, on-board intrusion detection. Second, a framework for swarm-based deployments that leverage federated learning and knowledge distillation to enable distributed training and lightweight model …
-
LIDIT: Low-Latency Intrusion Detection in IoMT Devices using TinyML
… an F1-score of 0.9988 with a recall of 0.9995. Post-training quantization using FLOAT16 and INT8 further reduced the model size to 0.23MB and 0.19 MB, respectively, making it suitable for real-time deployment. The system was successfully deployed on a Raspberry Pi Zero 2 W and evaluated under a …
-
Optimization of battery AI models for edge deployment: A systematic study of model compression techniques and hardware-aware efficiency
… execution. The baseline model and its original training were provided by Cognivity AI; model development is therefore outside the scope of this thesis. The study uses the provided model and its established preprocessing pipeline, with battery-level data separation for evaluation. The workflow …
-
Deep Reinforcement Learning for Multirotor Flight Control: A Comparative Study of Sim-to-Real Training and Real-World Performance
… error by up to 36 % and inference time by 26 %. Post-training quantization further reduced inference latency by ≈40 % with negligible performance loss. Incorporating trajectory tracking during training decreased tracking error by ≈75 % and eliminated temporal lag. The optimal training …
-
Compression of models and data in deep learning
… to the size of neural networks and apply to both training and inference. Compressing neural networks to make them train and run more efficiently is therefore crucial and has been a parallel line of research from the early days of neural networks development. The two main compression techniques in …
-
Energy-Aware TinyML for Ambient-Powered, Hardware-Constrained IoT Nodes
… The baseline models were further optimized using post-training quantization (PTQ), quantization-aware training (QAT), and a two-stage magnitude-based pruning method. Different optimization orders were compared with respect to model size, reconstruction quality, classifier accuracy, and estimated …
Page 1 of 2