7 citations · 17 across the 6 of their papers we have counts for
7 papers
A Selective Quantization Tuner for ONNX Models
Nikolaos Louloudakis, Ajitha Rajan
Quantization reduces the precision of deep neural networks to lower model size and computational demands, but often at the expense of accuracy. Fully quantized models can suffer si…
DiTOX: Fault Detection and Localization in the ONNX Optimizer
Nikolaos Louloudakis, Ajitha Rajan
The ONNX Optimizer, part of the official ONNX repository and widely adopted for graph-level model optimizations, is used by default to optimize ONNX models. Despite its popularity,…
FetaFix: Automatic Fault Localization and Repair of Deep Learning Model Conversions
Nikolaos Louloudakis, Perry Gibson, José Cano +1
Converting deep learning models between frameworks is a common step to maximize model compatibility across devices and leverage optimization features that may be exclusively provid…
DeltaNN: Assessing the Impact of Computational Environment Parameters on the Performance of Image Recognition Models
Nikolaos Louloudakis, Perry Gibson, José Cano +1
Image recognition tasks typically use deep learning and require enormous processing power, thus relying on hardware accelerators like GPUs and TPUs for fast, timely processing. Fai…
Fault Localization for Buggy Deep Learning Framework Conversions in Image Recognition
Nikolaos Louloudakis, Perry Gibson, José Cano +1
When deploying Deep Neural Networks (DNNs), developers often convert models from one deep learning framework to another (e.g., TensorFlow to PyTorch). However, this process is erro…
Exploring Robustness of Image Recognition Models on Hardware Accelerators
Nikolaos Louloudakis, Perry Gibson, José Cano +1
As the usage of Artificial Intelligence (AI) on resource-intensive and safety-critical tasks increases, a variety of Machine Learning (ML) compilers have been developed, enabling c…
Exploring Effects of Computational Parameter Changes to Image Recognition Systems
Nikolaos Louloudakis, Perry Gibson, José Cano +1
Image recognition tasks typically use deep learning and require enormous processing power, thus relying on hardware accelerators like GPUs and FPGAs for fast, timely processing. Fa…