國立虎尾科技大學 |

Analog IC Placement Generation via Neural Networks from Unlabeled Data

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Analog IC Placement Generation via Neural Networks from Unlabeled Data/ by António Gusmão, Nuno Horta, Nuno Lourenço, Ricardo Martins.
作者:	Gusmão, António.
其他作者:	Martins, Ricardo.
面頁冊數:	XIII, 87 p. 68 illus., 39 illus. in color.online resource. :
Contained By:	Springer Nature eBook
標題:	Machine Learning. -
電子資源:	https://doi.org/10.1007/978-3-030-50061-0
ISBN:	9783030500610

Analog IC Placement Generation via Neural Networks from Unlabeled Data
Gusmão, António.

Analog IC Placement Generation via Neural Networks from Unlabeled Data[electronic resource] /by António Gusmão, Nuno Horta, Nuno Lourenço, Ricardo Martins. - 1st ed. 2020. - XIII, 87 p. 68 illus., 39 illus. in color.online resource. - SpringerBriefs in Applied Sciences and Technology,2191-530X. - SpringerBriefs in Applied Sciences and Technology,.

Introduction -- Related Work: Machine Learning and Electronic Design Automation -- Unlabeled Data and Artificial Neural Networks -- Placement Loss: Placement Constraints Description and Satisfiability Evaluation -- Experimental Results in Industrial Case Studies -- Conclusions. .

In this book, innovative research using artificial neural networks (ANNs) is conducted to automate the placement task in analog integrated circuit layout design, by creating a generalized model that can generate valid layouts at push-button speed. Further, it exploits ANNs’ generalization and push-button speed prediction (once fully trained) capabilities, and details the optimal description of the input/output data relation. The description developed here is chiefly reflected in two of the system’s characteristics: the shape of the input data and the minimized loss function. In order to address the latter, abstract and segmented descriptions of both the input data and the objective behavior are developed, which allow the model to identify, in newer scenarios, sub-blocks which can be found in the input data. This approach yields device-level descriptions of the input topology that, for each device, focus on describing its relation to every other device in the topology. By means of these descriptions, an unfamiliar overall topology can be broken down into devices that are subject to the same constraints as a device in one of the training topologies. In the experimental results chapter, the trained ANNs are used to produce a variety of valid placement solutions even beyond the scope of the training/validation sets, demonstrating the model’s effectiveness in terms of identifying common components between newer topologies and reutilizing the acquired knowledge. Lastly, the methodology used can readily adapt to the given problem’s context (high label production cost), resulting in an efficient, inexpensive and fast model. .

ISBN: 9783030500610

Standard No.: 10.1007/978-3-030-50061-0doiSubjects--Topical Terms:

1137723
Machine Learning.

LC Class. No.: Q325.5-.7

Dewey Class. No.: 006.31

Analog IC Placement Generation via Neural Networks from Unlabeled Data
LDR:03397nam a22004095i 4500 001 1024477
003 DE-He213
005 20200703095136.0
007 cr nn 008mamaa
008 210318s2020 gw | s |||| 0|eng d
020 $a 9783030500610 $9 978-3-030-50061-0
024 7 $a 10.1007/978-3-030-50061-0 $2 doi
035 $a 978-3-030-50061-0
050 4 $a Q325.5-.7
050 4 $a TK7882.P3
072 7 $a UYQM $2 bicssc
072 7 $a COM004000 $2 bisacsh
072 7 $a UYQM $2 thema
082 0 4 $a 006.31 $2 23
100 1 $a Gusmão, António. $e author. $0 (orcid)0000-0001-7362-2407 $1 https://orcid.org/0000-0001-7362-2407 $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1320634
245 1 0 $a Analog IC Placement Generation via Neural Networks from Unlabeled Data $h [electronic resource] / $c by António Gusmão, Nuno Horta, Nuno Lourenço, Ricardo Martins.
250 $a 1st ed. 2020.
264 1 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2020.
300 $a XIII, 87 p. 68 illus., 39 illus. in color. $b online resource.
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
347 $a text file $b PDF $2 rda
490 1 $a SpringerBriefs in Applied Sciences and Technology, $x 2191-530X
505 0 $a Introduction -- Related Work: Machine Learning and Electronic Design Automation -- Unlabeled Data and Artificial Neural Networks -- Placement Loss: Placement Constraints Description and Satisfiability Evaluation -- Experimental Results in Industrial Case Studies -- Conclusions. .
520 $a In this book, innovative research using artificial neural networks (ANNs) is conducted to automate the placement task in analog integrated circuit layout design, by creating a generalized model that can generate valid layouts at push-button speed. Further, it exploits ANNs’ generalization and push-button speed prediction (once fully trained) capabilities, and details the optimal description of the input/output data relation. The description developed here is chiefly reflected in two of the system’s characteristics: the shape of the input data and the minimized loss function. In order to address the latter, abstract and segmented descriptions of both the input data and the objective behavior are developed, which allow the model to identify, in newer scenarios, sub-blocks which can be found in the input data. This approach yields device-level descriptions of the input topology that, for each device, focus on describing its relation to every other device in the topology. By means of these descriptions, an unfamiliar overall topology can be broken down into devices that are subject to the same constraints as a device in one of the training topologies. In the experimental results chapter, the trained ANNs are used to produce a variety of valid placement solutions even beyond the scope of the training/validation sets, demonstrating the model’s effectiveness in terms of identifying common components between newer topologies and reutilizing the acquired knowledge. Lastly, the methodology used can readily adapt to the given problem’s context (high label production cost), resulting in an efficient, inexpensive and fast model. .
650 1 4 $a Machine Learning. $3 1137723
650 0 $a Machine learning. $3 561253
700 1 $a Martins, Ricardo. $e author. $1 https://orcid.org/0000-0002-8251-1415 $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1320635
700 1 $a Lourenço, Nuno. $e author. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1264798
700 1 $a Horta, Nuno. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1066525
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
776 0 8 $i Printed edition: $z 9783030500603
776 0 8 $i Printed edition: $z 9783030500627
830 0 $a SpringerBriefs in Applied Sciences and Technology, $x 2191-530X $3 1253575
856 4 0 $u https://doi.org/10.1007/978-3-030-50061-0
912 $a ZDB-2-SCS
912 $a ZDB-2-SXCS
950 $a Computer Science (SpringerNature-11645)
950 $a Computer Science (R0) (SpringerNature-43710)