Corrigendum to: A Comprehensive Review on Deep Learning Techniques in Alzheimer’s Disease Diagnosis

View at publisher Summarise with VIRAT
Authors: Anjali Mahavar, Atul Patel, Ashish D. Patel
Cited by: 0
References: 1

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

In the originally published article entitled "A Comprehensive Review on Deep Learning Techniques in Alzheimer's Disease Diagnosis", published in "Current Topics in Medicinal Chemistry" Vol: 25 Issue: 04 [1], certain phrases and expressions were unclear, which may have affected readability. These have now been revised to improve clarity and ensure that the intended meaning is accurately conveyed. The corrections do not affect the results, interpretations, or conclusions of the article. The original article can be found online at https://www.eurekaselect.com/article/140894 Details of the error and a correction are provided here: ORIGINAL Moreover, DBN is a graphical model that investigators use to obtain a deep hierarchical representation of training data and is frequently used for AD detection. An unsupervised probabilistic Deep Learning Technique is created by pre-training DBN models using the greedy learning approach. From bottom to top, layers of RBMs are stacked to create the DBN architecture. Each RBM layer includes both a visible and concealed layer. The top two levels of the DBN structure have an undirected or symmetric link, whereas the lowest layers have a direct connection. DBN building is comparable to RBM construction in that the first RBM is made through training, after which the weights are fixed, and the concealed layer is established as the RBM's next visible layer. The next RBMs go through this procedure iteratively [79]. CORRECTED Moreover, DBN is a graphical model that investigators use to obtain a deep hierarchical representation of training data and is frequently used for AD detection. An unsupervised probabilistic Deep Learning Technique is created by pre-training DBN models using the greedy learning approach. From bottom to top, layers of RBMs are stacked to create the DBN architecture. Each RBM layer includes both a visible and hidden layer. The top two levels of the DBN structure have an undirected or symmetric link, whereas the lowest layers have a direct connection. DBN building is comparable to RBM construction in that the first RBM is made through training, after which the weights are fixed, and the hidden layer is established as the RBM's next visible layer. The next RBMs go through this procedure iteratively [79]. The authors apologize for any inconvenience caused.

Fields of Study & Subjects

Dementia and Cognitive Impairment Research Artificial Intelligence in Healthcare Alzheimer's disease research and treatments

Publication details

Journal / source
Current Topics in Medicinal Chemistry
Volume
26
Issue
7
Pages
779–779
Publication date
1 March 2026
Language
EN