Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
Retraction Notice: Leveraging Deep Learning Methodologies in Data Science Practices: A Systematic analysis
0
Zitationen
6
Autoren
2024
Jahr
Abstract
This paper proposes a systematic analysis of using deep mastering methodologies in statistics technology practices for the cause of leveraging the strength of deep mastering algorithms. It presents an overview of the exceptional types of deep gaining knowledge of methodologies and architectures in addition to their application within the various areas of records technology. Similarly, it critiques the prevailing literature and famous several useful findings regarding the usage of deep mastering in facts science and also the potential demanding situations and possibilities that could come in conjunction with it. It details the coding and implementation of numerous deep mastering fashions such as convolutional neural networks, deep belief networks, recurrent neural networks, and lengthy quick term memory (LSTM). Additionally, it presents an in-intensity analysis of the professionals and cons of the usage of deep gaining knowledge of for information technology. Eventually, it gives guidelines on a way to effectively use deep studying in facts technological know-how.
Ähnliche Arbeiten
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
2017 · 20.311 Zit.
Generative Adversarial Nets
2023 · 19.841 Zit.
Visualizing and Understanding Convolutional Networks
2014 · 15.238 Zit.
"Why Should I Trust You?"
2016 · 14.210 Zit.
On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper)
2024 · 13.104 Zit.