Ensembles of feedforward-designed convolutional neural networks

01/08/2019
by   Yueru Chen, et al.
0

An ensemble method that fuses the output decision vectors of multiple feedforward-designed convolutional neural networks (FF-CNNs) to solve the image classification problem is proposed in this work. To enhance the performance of the ensemble system, it is critical to increasing the diversity of FF-CNN models. To achieve this objective, we introduce diversities by adopting three strategies: 1) different parameter settings in convolutional layers, 2) flexible feature subsets fed into the Fully-connected (FC) layers, and 3) multiple image embeddings of the same input source. Furthermore, we partition input samples into easy and hard ones based on their decision confidence scores. As a result, we can develop a new ensemble system tailored to hard samples to further boost classification accuracy. Experiments are conducted on the MNIST and CIFAR-10 datasets to demonstrate the effectiveness of the ensemble method.

READ FULL TEXT
research
02/06/2019

Semi-supervised learning via Feedforward-Designed Convolutional Neural Networks

A semi-supervised learning framework using the feedforward-designed conv...
research
10/05/2018

Interpretable Convolutional Neural Networks via Feedforward Design

The model parameters of convolutional neural networks (CNNs) are determi...
research
07/04/2023

DeepFlorist: Rethinking Deep Neural Networks and Ensemble Learning as A Meta-Classifier For Object Classification

In this paper, we propose a novel learning paradigm called "DeepFlorist"...
research
03/19/2020

Ensemble learning in CNN augmented with fully connected subnetworks

Convolutional Neural Networks (CNNs) have shown remarkable performance i...
research
02/12/2023

Autoselection of the Ensemble of Convolutional Neural Networks with Second-Order Cone Programming

Ensemble techniques are frequently encountered in machine learning and e...
research
07/20/2018

Ensemble of Deep Learned Features for Melanoma Classification

The aim of this work is to propose an ensemble of descriptors for Melano...
research
02/25/2019

Visualization, Discriminability and Applications of Interpretable Saak Features

In this work, we study the power of Saak features as an effort towards i...

Please sign up or login with your details

Forgot password? Click here to reset