• Home
  • Search
  • Convolutional Neural Network with Discriminant Criterion for Input of Each Neuron in Output Layer
  • Cite Icon4
  • https://doi.org/10.1007/978-3-030-04167-0_30Copy DOI Icon

Convolutional Neural Network with Discriminant Criterion for Input of Each Neuron in Output Layer

  • Jan 1, 2018
  • Hidenori Ide +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Deep convolutional neural network (CNN) performs the state-of-the-art performance in image classification problems. When the neural network is trained for a multi-classes classification problem, each neuron of the output layer of the network is trained to solve the 2 classes classification problem which classifies target class and the rest of the classes. Since the posterior probability of a class can be expressed as soft-max function when the class conditional probabilities of each class are given as the Gaussian distribution with the different means and the same variance, the classifier with soft-max activation function becomes ideal when the input of the neuron in the output layer are given as the Gaussian distributions. Thus it is expected that the former layers in the CNN are constructing the good input for each neuron in the output layer in the learning process. To improve or accelerate the discrimination at the neurons in the output layer, this paper proposes to apply the discriminant criterion to the input value of each neuron in the output layer. The proposed objective function of the deep CNN is given as the sum of the discriminant criterion and the standard cross entropy loss. The results of experiments on MNIST, CIFAR-10 and CIFAR-100 show that the proposed method can improve the performance of classification and classify each class clearly.

Similar Papers
  • Research Article
  • Citations20

New neuron models for simulating rotating electrical machines and load forecasting problems

  • Oct 25, 1999
  • Electric Power Systems Research
  • D.K Chaturvedi +2
  • Research Article
  • Citations2

FAST NEURAL NETWORK ALGORITHM FOR SOLVING CLASSIFICATION TASKS

  • Jul 12, 2014
  • VCU Scholars Compass (Virginia Commonwealth University)
  • Noor Albarakati
  • Conference Article
  • Citations11

Fast neural network algorithm for solving classification tasks: Batch error back-propagation algorithm

  • Apr 01, 2013
  • Noor Albarakati +1
  • Research Article
  • Citations19

Cascaded normalizations for spatial integration in the primary visual cortex of primates.

  • Aug 01, 2022
  • Cell Reports
  • Yang Li +11
  • PDF
  • Research Article
  • Citations12

Prediction of Flight Status of Logistics UAVs Based on an Information Entropy Radial Basis Function Neural Network

  • May 24, 2021
  • Sensors (Basel, Switzerland)
  • Qin Yang +5
  • Research Article
  • Citations6

Live to learn: learning rules-based artificial neural network

  • Jan 01, 2021
  • Indonesian Journal of Electrical Engineering and Computer Science
  • Aseel Shakir I Hilaiwah +3
  • Research Article
  • Citations12

A Self Supervised Bi-directional Neural Network (BDSONN) Architecture for Object Extraction Guided by Beta Activation Function and Adaptive Fuzzy Context Sensitive Thresholding

  • Apr 20, 2008
  • Zenodo (CERN European Organization for Nuclear Research)
  • Siddhartha Bhattacharyya +3
  • Conference Article
  • Citations9

The Subsurface Objects Classification using a Convolutional Neural Network

  • Oct 01, 2019
  • Mostafa Elsaadouny +2
  • Conference Article
  • Citations1

Classification of Remote Sensing scenes using Semi-Supervised Domain Adaptation based on Entropy Adversarial Optimization

  • Apr 01, 2021
  • Tariq Lasloum +2
  • Research Article
  • Citations10

Neural Network Model To Predict Slug Frequency of Low-Viscosity Two-Phase Flow

  • Nov 11, 2020
  • SPE Journal
  • Ghassan H Abdul-Majeed +3
  • Research Article
  • Citations4

IMPLEMENTASI JARINGAN SYARAF TIRUAN BACKPROPAGATION DENGAN ALGORITMA CONJUGATE GRADIENT UNTUK KLASIFIKASI KONDISI RUMAH (Studi Kasus di Kabupaten Cilacap Tahun 2018)

  • Feb 28, 2020
  • Jurnal Gaussian
  • Johanes Roisa Prabowo +2
  • Research Article
  • Citations193

Classification of Sea Ice Types in ENVISAT Synthetic Aperture Radar Images

  • May 01, 2013
  • IEEE Transactions on Geoscience and Remote Sensing
  • Natalia Yu Zakhvatkina +4
  • Conference Article

Implementation of a neural network based system for estimating the strength of a board using mixed signals

  • Oct 14, 2003
  • H Saboksayr +3
  • Research Article
  • Citations6

PENGENALAN ISYARAT TANGAN STATIS PADA SISTEM ISYARAT BAHASA INDONESIA BERBASIS JARINGAN SYARAF TIRUAN PERAMBATAN BALIK

  • May 23, 2011
  • MAKARA of Technology Series
  • Farida Asriani +1
  • Research Article
  • Citations27

Using superior colliculus principles of multisensory integration to reverse hemianopia

  • Feb 27, 2020
  • Neuropsychologia
  • Barry E Stein +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.