A survey of deep network techniques all classifiers can adopt

Ghods, Alireza; Cook, Diane J.

doi:10.1007/s10618-020-00722-8

Cited by 18 publications

(8 citation statements)

References 105 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The amounts of data and computational power required for learning have increased. Deep learning uses DNNs with hundreds of layers and a large number of parameters related to structure [145][146][147][148][149][150][151][152][153][154][155][156][157][158][159][160][161]. Therefore, it is prone to overfitting, which is a condition where the learning data are overfitted, generalization is not possible, and high accuracy cannot be achieved with unknown data.…”

Section: Amounts Of Data and Computational Powermentioning

confidence: 99%

Applications of Deep Learning for Drug Discovery Systems with BigData

Matsuzaka

Yashiro

2022

BioMedInformatics

View full text Add to dashboard Cite

The adoption of “artificial intelligence (AI) in drug discovery”, where AI is used in the process of pharmaceutical research and development, is progressing. By using the ability to process large amounts of data, which is a characteristic of AI, and achieving advanced data analysis and inference, there are benefits such as shortening development time, reducing costs, and reducing the workload of researchers. There are various problems in drug development, but the following two issues are particularly problematic: (1) the yearly increases in development time and cost of drugs and (2) the difficulty in finding highly accurate target genes. Therefore, screening and simulation using AI are expected. Researchers have high demands for data collection and the utilization of infrastructure for AI analysis. In the field of drug discovery, for example, interest in data use increases with the amount of chemical or biological data available. The application of AI in drug discovery is becoming more active due to improvement in computer processing power and the development and spread of machine-learning frameworks, including deep learning. To evaluate performance, various statistical indices have been introduced. However, the factors affected in performance have not been revealed completely. In this study, we summarized and reviewed the applications of deep learning for drug discovery with BigData.

show abstract

Section: Amounts Of Data and Computational Powermentioning

confidence: 99%

Applications of Deep Learning for Drug Discovery Systems with BigData

Matsuzaka

Yashiro

2022

BioMedInformatics

View full text Add to dashboard Cite

show abstract

“…For example, not having a sufficient sample size incorporates potential bias or noise in the trained algorithm, which results in low replicability and performance [64,65]. In response, efficient resampling schemes for classifiers can be proposed for addressing the limited sample size problem and upgrading their generalizability accordingly, which is an important aspect in technology adoption, as shown in several investigations [21,66]. Generalizability problems are one of the main barriers to the effective implementation of classifiers in the clinical context.…”

Section: Calculation Of Fuzzy Relative Priorities and Interdependence...mentioning

confidence: 99%

A Novel Integration of IF-DEMATEL and TOPSIS for the Classifier Selection Problem in Assistive Technology Adoption for People with Dementia

Ortíz‐Barrios

García-Constantino

Nugent

et al. 2022

IJERPH

View full text Add to dashboard Cite

The classifier selection problem in Assistive Technology Adoption refers to selecting the classification algorithms that have the best performance in predicting the adoption of technology, and is often addressed through measuring different single performance indicators. Satisfactory classifier selection can help in reducing time and costs involved in the technology adoption process. As there are multiple criteria from different domains and several candidate classification algorithms, the classifier selection process is now a problem that can be addressed using Multiple-Criteria Decision-Making (MCDM) methods. This paper proposes a novel approach to address the classifier selection problem by integrating Intuitionistic Fuzzy Sets (IFS), Decision Making Trial and Evaluation Laboratory (DEMATEL), and the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS). The step-by-step procedure behind this application is as follows. First, IF-DEMATEL was used for estimating the criteria and sub-criteria weights considering uncertainty. This method was also employed to evaluate the interrelations among classifier selection criteria. Finally, a modified TOPSIS was applied to generate an overall suitability index per classifier so that the most effective ones can be selected. The proposed approach was validated using a real-world case study concerning the adoption of a mobile-based reminding solution by People with Dementia (PwD). The outputs allow public health managers to accurately identify whether PwD can adopt an assistive technology which results in (i) reduced cost overruns due to wrong classification, (ii) improved quality of life of adopters, and (iii) rapid deployment of intervention alternatives for non-adopters.

show abstract

“…Specifically, the pooling operation computes the local statistical characteristics of a location to replace the elements of the input data on that location region. rough the operation of the pooling layer, the number of parameters in the entire network is reduced, which alleviates the complexity of parameter calculation and storage [15,16]. e average pooling operation can be expressed as Computational Intelligence and Neuroscience Setting j…”

Section: Convolutionmentioning

confidence: 99%

Music Score Recognition Method Based on Deep Learning

Lin

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In recent years, the recommendation application of artificial intelligence and deep music has gradually become a research hotspot. As a complex machine learning algorithm, deep learning can extract features with value laws through training samples. The rise of deep learning network will promote the development of artificial intelligence and also provide a new idea for music score recognition. In this paper, the improved deep learning algorithm is applied to the research of music score recognition. Based on the traditional neural network, the attention weight value improved convolutional neural network (CNN) and high execution efficiency deep belief network (DBN) are introduced to realize the feature extraction and intelligent recognition of music score. Taking the feature vector set extracted by CNN-DBN as input set, a feature learning algorithm based on CNN&DBN was established to extract music score. Experiments show that the proposed model in a variety of different types of polyphony music recognition showed more accurate recognition and good performance; the recognition rate of the improved algorithm applied to the soundtrack identification is as high as 98.4%, which is significantly better than those of other classic algorithms, proving that CNN&DBN can achieve better effect in music information retrieval. It provides data support for constructing knowledge graph in music field and indicates that deep learning has great research value in music retrieval field.

show abstract

A survey of deep network techniques all classifiers can adopt

Cited by 18 publications

References 105 publications

Applications of Deep Learning for Drug Discovery Systems with BigData

Applications of Deep Learning for Drug Discovery Systems with BigData

A Novel Integration of IF-DEMATEL and TOPSIS for the Classifier Selection Problem in Assistive Technology Adoption for People with Dementia

Music Score Recognition Method Based on Deep Learning

Contact Info

Product

Resources

About