你好! Shipping to Taiwan with premium packaging for just NT$300 

Ship to
Taiwan
0

My Account

  • argentina
  • chile
  • colombia
  • españa
  • méxico
  • perú
  • estados unidos
  • internacional

menu

Select your country

Americas

Europe

Rest of the world

portada Enhancing Deep Learning Performance Using Displace (in Portuguese)
Type
Physical Book
Publisher
Author
Language
Portuguese
Pages
100
Format
Paperback
ISBN13
9786525230566
Edited in
Brasil

Enhancing Deep Learning Performance Using Displace (in Portuguese)

Mac ªdo (Author) · Docuprint · Paperback

Enhancing Deep Learning Performance Using Displace (in Portuguese) - Mac ªDo

Cheaper New Book Imported to Taiwan
Delivery: 15 Oct - 03 Nov Shipping: 17 to 25 business days.
NT$ 920
Faster New Book Imported to Taiwan
Delivery: 08 Oct - 21 Oct Shipping: 12 to 16 business days.
NT$ 960
NT$ 920

Choose the list to add your product or create one New List

Go to My Wishlists
Calculate shipping cost

Synopsis "Enhancing Deep Learning Performance Using Displace (in Portuguese)"

Recently, deep learning has caused a significant impact on computer vision, speech recognition, and natural language understanding. In spite of the remarkable advances, deep learning recent performance gains have been modest and usually rely on increasing the depth of the models, which often requires more computational resources such as processing time and memory usage. To tackle this problem, we turned our attention to the interworking between the activation functions and the batch normalization, which is virtually mandatory currently. In this work, we propose the activation function Displaced Rectifier Linear Unit (DReLU) by conjecturing that extending the identity function of ReLU to the third quadrant enhances compatibility with batch normalization. Moreover, we used statistical tests to compare the impact of using distinct activation functions (ReLU, LReLU, PReLU, ELU, and DReLU) on the learning speed and test accuracy performance of VGG and Residual Networks state-of-the-art models. These convolutional neural networks were trained on CIFAR-10 and CIFAR-100, the most commonly used deep learning computer vision datasets. The results showed DReLU speeded up learning in all models and datasets. Besides, statistical significant performance assessments (p

Customers reviews

More customer reviews
  • 0% (0)
  • 0% (0)
  • 0% (0)
  • 0% (0)
  • 0% (0)

Frequently Asked Questions about the Book

Is the book original?

All books in our catalog are Original.

In what language is the book written?

The book is written in Portuguese.

What is the format of this book?

The binding of this edition is Paperback.

Questions and Answers about the Book

Do you have a question about the book? Login to be able to add your own question.

Opinions about Bookdelivery

More customer reviews