Abdul Wahid Memon

TL;DR: Milepost GCC is described, the first publicly-available open-source machine learning-based compiler that automatically adapts the internal optimization heuristic at function-level granularity to improve execution time, code size and compilation time of a new program on a given architecture.

TL;DR: This work presents a practical and collaborative solution via light-weight wrappers around any software piece when more than one implementation or optimization choice available to be able to predict best optimizations and improve compilers and hardware depending on usage scenarios and requirements.

TL;DR: All the past research artifacts including hundreds of codelets, numerical applications, data sets, models, universal experimental analysis and auto-tuning pipelines, self-tuned machine learning based meta compiler, and unified statistical analysis and machine learning plugins are shared in a public repository to initiate systematic, reproducible and collaborative R\&D with a new publication model.

TL;DR: This paper proposes a robust and computationally-efficient ANPDR system which uses Deformable Part Models (DPM) for extracting number plate features from training images, Structural Support Vector Machine (SSVM) for training a number plate detector with the extracted DPM features, several image enhancement operations on the extracted number plate, and Optical Character Recognition for extracting the numbers from the plate.

TL;DR: Notre cadre de travail open-source et notre depot (repository) public permettent de rendre le reglage automatique et l'apprentissage d’optimisations praticable, which est de permettre a la communaute de valider les resultats, les comportements inattendus et les modeles conduisant a de mauvaises predictions.