An Intelligent Multi-View Active Learning Method Based on a Double-Branch Network

Abstract

Artificial intelligence is one of the most popular topics in computer science. Convolutional neural network (CNN), which is an important artificial intelligence deep learning model, has been widely used in many fields. However, training a CNN requires a large amount of labeled data to achieve a good performance but labeling data is a time-consuming and laborious work. Since active learning can effectively reduce the labeling effort, we propose a new intelligent active learning method for deep learning, which is called multi-view active learning based on double-branch network (MALDB). Different from most existing active learning methods, our proposed MALDB first integrates two Bayesian convolutional neural networks (BCNNs) with different structures as two branches of a classifier to learn the effective features for each sample. Then, MALDB performs data analysis on unlabeled dataset and queries the useful unlabeled samples based on different characteristics of two branches to iteratively expand the training dataset and improve the performance of classifier. Finally, MALDB combines multiple level information from multiple hidden layers of BCNNs to further improve the stability of sample selection. The experiments are conducted on five extensively used datasets, Fashion-MNIST, Cifar-10, SVHN, Scene-15 and UIUC-Sports, the experimental results demonstrate the validity of our proposed MALDB.

Exploring Artificial Intelligence Architecture in Data Cleaning Based on Bayesian Networks

“…The conditional probability table stores the probability of occurrence of the current node under different parent nodes, as shown in Tables 1, 2, and 3. The strength of dependence between nodes can be expressed through conditional probability [12]. Variables in Bayesian networks can be either continuous variables or discrete variables.…”

A bibliography experiment on research within the scope of industry 4.0 application areas in sports

“…Sanayi 4.0 kavramı dördüncü endüstri devrimi için kullanılan bir terimdir (Drath ve Horc., 2016, ss. [56][57][58]. Endüstri 4.0 en kapsamlı tanımıyla, bireysel müşteri ihtiyaçlarını karşılamak amacıyla endüstriyel üretimi temsil eden, verimlilik, karlılık ve kalite gibi hedeflerle, örgütlerde yönetim, ar-ge, üretim, pazarlama ve üretilen malların döngüsüne kadar geniş bir alanı etkileyen işletme üretim süreçlerinin dijitalleşmesidir (Neugebauer vd., 2016).…”