NDLTD Global ETD Search
  • Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 1
  • Tagged with
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.

Search results

Showing 1 to 2 of 2 (0.125 seconds)

Spelling suggestions: "subject:"adaptive sharpness aware minimization"" "subject:"adaptive sharpness aware minimizations""

1

Efficientnext: Efficientnet For Embedded Systems

Deokar, Abhishek 05 1900 (has links)
Indiana University-Purdue University Indianapolis (IUPUI) / Convolutional Neural Networks have come a long way since AlexNet. Each year the limits of the state of the art are being pushed to new levels. EfficientNet pushed the performance metrics to a new high and EfficientNetV2 even more so. Even so, architectures for mobile applications can benefit from improved accuracy and reduced model footprint. The classic Inverted Residual block has been the foundation upon which most mobile networks seek to improve. EfficientNet architecture is built using the same Inverted Residual block. In this thesis we experiment with Harmonious Bottlenecks in place of the Inverted Residuals to observe a reduction in the number of parameters and improvement in accuracy. The designed network is then deployed on the NXP i.MX 8M Mini board for Image classification. / 2023-10-11
Convolutional Neural Networks
Coordinate Attention
Adaptive Sharpness Aware Minimization
Harmonious Bottleneck
Sandglass Bottleneck
Inverted Residual
Fused-MBConv
CIFAR-10
NXP i.MX 8M Mini
GELU
Swish
ReLU6
2

EFFICIENTNEXT: EFFICIENTNET FOR EMBEDDED SYSTEMS

Abhishek Rajendra Deokar (12456477) 12 July 2022 (has links)
<p>Convolutional Neural Networks have come a long way since  AlexNet. Each year the limits of the state of the art are being pushed to new  levels. EfficientNet pushed the performance metrics to a new high and EfficientNetV2 even more so. Even so, architectures for mobile applications can benefit from improved accuracy and reduced model footprint. The classic Inverted Residual block has been the foundation upon which most mobile networks seek to improve. EfficientNet architecture is built using the same Inverted Residual block. In this paper we experiment with Harmonious Bottlenecks in  place of the Inverted Residuals to observe a reduction in the number of parameters and improvement in accuracy. The designed network is then deployed on the NXP i.MX 8M Mini board for Image classification.</p>
Digital processor architectures
Convolutional Neural Network
Coordinate Attention
Adaptive Sharpness Aware Minimization
Harmonious Bottleneck
Sandglass Bottleneck
Inverted Residual
Fused-MBConv
CIFAR-10
NXP i.MX 8M Mini
GELUs activation function
Computer Engineering

Page generated in 0.1308 seconds