Technical Report: Combining knowledge from Transfer Learning during training and Wide Resnets

06/20/2022
by   Wolfgang Fuhl, et al.
0

In this report, we combine the idea of Wide ResNets and transfer learning to optimize the architecture of deep neural networks. The first improvement of the architecture is the use of all layers as information source for the last layer. This idea comes from transfer learning, which uses networks pre-trained on other data and extracts different levels of the network as input for the new task. The second improvement is the use of deeper layers instead of deeper sequences of blocks. This idea comes from Wide ResNets. Using both optimizations, both high data augmentation and standard data augmentation can produce better results for different models. Link: https://github.com/wolfgangfuhl/PublicationStuff/tree/master/TechnicalReport1/Supp

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/24/2023

HULAT at SemEval-2023 Task 10: Data augmentation for pre-trained transformers applied to the detection of sexism in social media

This paper describes our participation in SemEval-2023 Task 10, whose go...
research
02/24/2023

HULAT at SemEval-2023 Task 9: Data augmentation for pre-trained transformers applied to Multilingual Tweet Intimacy Analysis

This paper describes our participation in SemEval-2023 Task 9, Intimacy ...
research
06/19/2018

Transfer Learning with Human Corneal Tissues: An Analysis of Optimal Cut-Off Layer

Transfer learning is a powerful tool to adapt trained neural networks to...
research
09/27/2020

Smart Irrigation IoT Solution using Transfer Learning for Neural Networks

In this paper we develop a reliable system for smart irrigation of green...
research
06/30/2022

Improving the Generalization of Supervised Models

We consider the problem of training a deep neural network on a given cla...
research
11/09/2020

MAGNeto: An Efficient Deep Learning Method for the Extractive Tags Summarization Problem

In this work, we study a new image annotation task named Extractive Tags...

Please sign up or login with your details

Forgot password? Click here to reset