Hasil Pencarian  ::  Simpan CSV :: Kembali

Hasil Pencarian

Ditemukan 5227 dokumen yang sesuai dengan query
cover
Easley, David
""Over the past decade there has been a growing public fascination with the complex connectedness of modern society. This connectedness is found in many incarnations: in the rapid growth of the Internet, in the ease with which global communication takes place, and in the ability of news and information as well as epidemics and financial crises to spread with surprising speed and intensity. These are phenomena that involve networks, incentives, and the aggregate behavior of groups of people; they are based on the links that connect us and the ways in which our decisions can have subtle consequences for others. This introductory undergraduate textbook takes an interdisciplinary look at economics, sociology, computing and information science, and applied mathematics to understand networks and behavior. It describes the emerging field of study that is growing at the interface of these areas, addressing fundamental questions about how the social, economic, and technological worlds are connected"--Provided by publisher."
New York: Cambridge University Press, 2018
303.483 3 EAS n
Buku Teks  Universitas Indonesia Library
cover
Hansen, Derek L.
Burlington, MA : Morgan Kaufmann, 2011
006.754 HAN a
Buku Teks  Universitas Indonesia Library
cover
Quesenbery, Whitney
Amsterdam : Elsevier, 2012
658.575 2 QUE g
Buku Teks  Universitas Indonesia Library
cover
"CONTENTS :
- A NOTE FROM OUR SPONSOR
- EXECUTIVE SUMMARY
- INTRODUCTION
- SECTION 1: WHERE ARE WE?
- SECTION 2: WHAT?S HOLDING US BACK?
- SECTION 3: FROM BLEEDING EDGE TO LEADING EDGE
- CONCLUSION & POLICY RECOMMENDATIONS
- REFERENCES
- ABOUT THE AUTHORS AND CONTRIBUTORS
- ABOUT THE CONTRIBUTING ORGANIZATIONS
- APPENDIX: MOBILE LEARNING SURVEY OVERVIEW "
Alexandria, VA: American Society for Training & Development, 2012
e20440895
eBooks  Universitas Indonesia Library
cover
Ari Nugroho
"ABSTRAK
Densely Connected Convolutional Networks (DenseNet) merupakan salah satu
model arsitektur Deep Learning yang menghubungkan setiap layer beserta feature-maps ke seluruh layer berikutnya, sehingga layer berikutnya menerima input
feature-maps dari seluruh layer sebelumnya. Karena padatnya arsitektur DenseNet
meyebabkan komputasi model memerlukan waktu lama dan pemakaian memory
GPU yang besar. Penelitian ini mengembangkan metode optimisasi DenseNet
menggunakan batching strategy yang bertujuan untuk mengatasi permasalahan
DenseNet dalam hal percepatan komputasi dan penghematan ruang memory GPU.
Batching strategy adalah metode yang digunakan dalam Stochastic Gradient
Descent (SGD) dimana metode tersebut menerapkan metode dinamik batching
dengan inisialisasi awal menggunakan ukuran batch kecil dan ditingkatkan
ukurannya secara adaptif selama training hingga sampai ukuran batch besar agar
terjadi peningkatan paralelisasi komputasi untuk mempercepat waktu pelatihan.
Metode batching strategy juga dilengkapi dengan manajemen memory GPU
menggunakan metode gradient accumulation. Dari hasil percobaan dan pengujian
terhadap metode tersebut dihasilkan peningkatan kecepatan waktu pelatihan hingga
1,7x pada dataset CIFAR-10 dan 1,5x pada dataset CIFAR-100 serta dapat
meningkatkan akurasi DenseNet. Manajemen memory yang digunakan dapat
menghemat memory GPU hingga 30% jika dibandingkan dengan native DenseNet.
Dataset yang digunakan menggunakan CIFAR-10 dan CIFAR-100 datasets.
Penerapan metode batching strategy tersebut terbukti dapat menghasilkan
percepatan dan penghematan ruang memory GPU.

ABSTRACT
Densely Connected Convolutional Networks (DenseNet) is one of the Deep
Learning architecture models that connect each layer and feature maps to all
subsequent layers so that the next layer receives input feature maps from all
previous layers. Because of its DenseNet architecture, computational models
require a long time and use large GPU memory. This research develops the
DenseNet optimization method using a batching strategy that aims to overcome the
DenseNet problem in terms of accelerating computing time and saving GPU
memory. Batching strategy is a method used in Stochastic Gradient Descent (SGD)
where the technique applies dynamic batching approach with initial initialization
using small batch sizes and adaptively increased size during training to large batch
sizes so that there is an increase in computational parallelization to speed up training
time. The batching strategy method is also equipped with GPU memory
management using the gradient accumulation method. From the results of
experiments and testing of these methods resulted in an increase in training time
speed of up to 1.7x on the CIFAR-10 dataset and 1.5x on the CIFAR-100 dataset
and can improve DenseNet accuracy. Memory management used can save GPU
memory up to 30% when compared to native DenseNet. The dataset used uses
CIFAR-10 and CIFAR-100 datasets. The application of the batching strategy
method is proven to be able to produce acceleration and saving of GPU memory."
2020
T-Pdf
UI - Tesis Membership  Universitas Indonesia Library
cover
Tartaron, Thomas F
New York: Cambridge University Press, 2013
387.509 TAR m
Buku Teks  Universitas Indonesia Library
cover
"This book showcases cutting-edge research papers from the 7th International Conference on Research into Design (ICoRD 2019)-the largest in India in this area-written by eminent researchers from across the world on design processes, technologies, methods and tools, and their impact on innovation, for supporting design for a connected world. The theme of ICoRD19 has been Design for a Connected World. While Design traditionally focused on developing products that worked on their own, an emerging trend is to have products with a smart layer that makes them context aware and responsive, individually and collectively, through collaboration with other physical and digital objects with which these are connected. The papers in this volume explore these themes, and their key focus is connectivity: how do products and their development change in a connected world? The volume will be of interest to researchers, professionals and entrepreneurs working in the areas on industrial design, manufacturing, consumer goods, and industrial management who are interested in the use of emerging technologies such as IOT, IIOT, Digital Twins, I4.0 etc. as well as new and emerging methods and tools to design new products, systems and services."
Singapore: Springer Nature, 2019
e20509873
eBooks  Universitas Indonesia Library
cover
"This book showcases cutting-edge research papers from the 7th International Conference on Research into Design (ICoRD 2019) - the largest in India in this area - written by eminent researchers from across the world on design processes, technologies, methods and tools, and their impact on innovation, for supporting design for a connected world. The theme of ICoRD19 has been Design for a Connected World. While Design traditionally focused on developing products that worked on their own, an emerging trend is to have products with a smart layer that makes them context aware and responsive, individually and collectively, through collaboration with other physical and digital objects with which these are connected. The papers in this volume explore these themes, and their key focus is connectivity: how do products and their development change in a connected world? The volume will be of interest to researchers, professionals and entrepreneurs working in the areas on industrial design, manufacturing, consumer goods, and industrial management who are interested in the use of emerging technologies such as IOT, IIOT, Digital Twins, I4.0 etc. as well as new and emerging methods and tools to design new products, systems and services."
Singapore: Springer Nature, 2019
e20509874
eBooks  Universitas Indonesia Library
cover
Abernathy, David
London: CA SAGE, 2017
910.21 ABE u
Buku Teks SO  Universitas Indonesia Library
cover
Abernathy, David
London: CA SAGE, 2017
910.21 ABE u
Buku Teks SO  Universitas Indonesia Library
<<   1 2 3 4 5 6 7 8 9 10   >>