Exploració per altres contribucions "Arnau Montañés, José María"
Ara es mostren els items 1-11 de 11
-
A hardware accelerator for ORB-SLAM
(Universitat Politècnica de Catalunya, 2019-10-17)
Projecte Final de Màster Oficial
Accés obertSimultaneous Localization And Mapping (SLAM) is a key component of self-driving cars. We study ORB-SLAM, a SLAM state-of-the-art solution, and develop a hardware accelerator for a critical part of it: ORB feature extraction. ... -
Acceleration of automatic speech recognition for low-power devices
(Universitat Politècnica de Catalunya, 2022-11-09)
Tesi
Accés obert(English) In this thesis, we study the challenges preventing ASR deployment on edge devices and propose innovations to tackle them, hopefully moving the technology a step forward to the future. First, we characterize ... -
An enegy-efficient FPGA accelerator for convolutional neural networks
(Universitat Politècnica de Catalunya, 2018-10-25)
Projecte Final de Màster Oficial
Accés obertThis project focuses on a state-of-the-art DNN specifically build for image clas sification. We develop a new architecture design that will run on an experimental Intel accelerator platform called HARP. We obtain low-power ... -
Characterization of Speech Recognition Systems on GPU Architectures
(Universitat Politècnica de Catalunya, 2016-07-04)
Projecte Final de Màster Oficial
Accés obertThis master thesis characterizes the performance and energy bottlenecks of speech recognition systems when running on modern GPU, with the aim of providing useful information for designing future GPU architectures, as well ... -
Energy Efficient Accelerator for Self Driving Cars
(Universitat Politècnica de Catalunya, 2018-10-15)
Projecte Final de Màster Oficial
Accés restringit per acord de confidencialitat -
Energy-efficient architectures for recurrent neural networks
(Universitat Politècnica de Catalunya, 2021-01-25)
Tesi
Accés obertDeep Learning algorithms have been remarkably successful in applications such as Automatic Speech Recognition and Machine Translation. Thus, these kinds of applications are ubiquitous in our lives and are found in a plethora ... -
High-performance and energy-efficient irregular graph processing on GPU architectures
(Universitat Politècnica de Catalunya, 2021-02-18)
Tesi
Accés obertGraph processing is an established and prominent domain that is the foundation of new emerging applications in areas such as Data Analytics and Machine Learning, empowering applications such as road navigation, social ... -
Implementación de una red neuronal en una FPGA
(Universitat Politècnica de Catalunya, 2017)
Treball Final de Grau
Accés restringit per acord de confidencialitat -
Improving instruction scheduling in GPGPUs
(Universitat Politècnica de Catalunya, 2022-06-23)
Projecte Final de Màster Oficial
Accés obertGPU architectures have become popular for executing general-purpose programs. Moreover, they are some of the most efficient architectures for machine learning applications which are among the most trendy and demanding ... -
Low-power accelerators for cognitive computing
(Universitat Politècnica de Catalunya, 2020-10-09)
Tesi
Accés obertDeep Neural Networks (DNNs) have achieved tremendous success for cognitive applications, and are especially efficient in classification and decision making problems such as speech recognition or machine translation. Mobile ... -
Ultra low-power, high-performance accelerator for speech recognition
(Universitat Politècnica de Catalunya, 2019-07-25)
Tesi
Accés obertAutomatic Speech Recognition (ASR) is undoubtedly one of the most important and interesting applications in the cutting-edge era of Deep-learning deployment, especially in the mobile segment. Fast and accurate ASR comes ...