1. Αποθετήριο Παραδοτέων Υποτρόφων Δράσεων ΕΣΠΑ Τριτοβάθμιας Εκπαίδευσης 2017-2023
2. Όλο το Αποθετήριο
3. Ερευνητικές ομάδες

Τύπος:	Ανακοίνωση σε συνέδριο
Τίτλος:	A design flow framework for Fully-Connected Neural Networks rapid prototyping
Συγγραφέας:	[EL] Ζομπάκης, Νικόλαος[EN] Zompakis, Nikolaos [EL] Αναγνώστος, Δημήτριος[EN] Anagnostos, Dimitrios [EL] Κολιογεώργη, Κωνσταντίνα[EN] Koliogeorgi, Konstantina [EL] Ζερβάκης, Γεώργιος[EN] Zervakis, Georgios [EL] Σιώζιος, Κωνσταντίνος[EN] Siozios, Kostas
Ημερομηνία:	Μαΐ-2019
Περίληψη:	The current work deploys a framework for rapid prototyping of Fully-Connected Neural Networks (FCNs). The scope is to provide an automatic design flow that generates a template-based VHDL code considering the accuracy, the resource utilization and the design complexity. More precisely, the deployed tool incorporates hardware optimizations in the implementation of the multiplications, the activation function and the definition of the fixed-point types providing user-defined configurations thought a GUI. The FCNs of two applications (Alexnet and Lenet) were implemented to evaluate our approach. The results seem promising and prove the design flexibility of our framework generating optimized code that exceeds the 10K lines for each hardware instance within a few hours, while preserving low levels of latency that does not exceed 400 cycles for our applications.
Γλώσσα:	Αγγλικά
Τόπος δημοσίευσης:	Crete, Greece
Σελίδες:	6
DOI:	10.1145/3312614.3312628
ISBN:	978-1-4503-6640-3
Θεματική κατηγορία:	[EL] Άλλες Επιστήμες Μηχανικού και Τεχνολογίες[EN] Other Engineering and Technologies
Λέξεις-κλειδιά:	fpga; neural networks; fully-connected; accuracy; rapid prototyping; DNN; vhdl; bit precision
Κάτοχος πνευματικών δικαιωμάτων:	© 2019 Copyright held by the owner/author(s). Publication rights licensed to ACM.
Όροι και προϋποθέσεις δικαιωμάτων:	Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from permissions@acm.org.
Ηλεκτρονική διεύθυνση του τεκμηρίου στον εκδότη:	https://dl.acm.org/doi/10.1145/3312614.3312628
Ηλεκτρονική διεύθυνση περιοδικού:	https://dl.acm.org/doi/proceedings/10.1145/3312614
Σελίδες τεκμηρίου (στην πηγή):	44-49
Όνομα εκδήλωσης:	COINS’19: International Conference on Omni-layer Intelligent systems
Τοποθεσία εκδήλωσης:	Crete Greece
Ημ/νία έναρξης εκδήλωσης:	05/05/2019
Ημ/νία λήξης εκδήλωσης:	07/05/2019
Σημειώσεις:	This research is co-financed by Greece and the European Union (European Social Fund- ESF) through the Operational Program “Human Resources Development, Education and Lifelong Learning 2014-2020” in the context of the project “Automated methodology for production and execution of data-centric multi-level approximate equivalent applications for heterogeneous computing platforms” (MIS 5005377).
Εμφανίζεται στις συλλογές:	Ερευνητικές ομάδες