Machine Learning and Deep Learning: Open Issues and Future Research Directions for the Next 10 Years
Abstract
With the development in technology, many other technologies like machine learning (ML), deep learning, blockchain technology, Internet of Things, and quantum computing have taken place in this current era. These technologies are helping human being to live their life comfortably and without any hurdle. Today, technology is helping human and protecting nature with minimum waste of available/limited resources. Among these inventions, ML and deep learning are two unique inventions which have attract many researchers or computer science researchers (or many research communities) to solve complex problems through ML. Today, ML use has been moved in many sectors to increase productivity of businesses; for example, for retail/marketing purpose, churn prediction of customers, for e-healthcare, and detecting disease in early stages. These are the few examples where ML is used in this current smart era. Together, this deep learning also has increased its importance over ML in many applications like bio-informatics, health informatics, identification of images or handwritten languages, and audio recognition. Many researchers get problematic scenario when they are not sure about particular use of machine and deep learning. This work fulfil such conditions/requirements and provide a complete details about ML and deep learning, i.e., with its evolution to forefront use, to use in many applications, to benefiting to the society, and to challenges and potential limitation in the respective learning techniques.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
DL's hidden weight and activation are non-interpretable.
“Reasoning of prediction unexplainable: DL result prediction follows the Black-Box testing approach. Thus, it is not capable of making any explainable predictions. Since DL's hidden weight and activation are non-interpretable, its predictions are considered as non-explainable [200].”
From A Review on Deep-Learning-Based Cyberbullying Detection (2023) · cites this paper as [200]
DL result prediction follows the Black-Box testing approach and is not capable of making explainable predictions.
“Reasoning of prediction unexplainable: DL result prediction follows the Black-Box testing approach. Thus, it is not capable of making any explainable predictions. Since DL's hidden weight and activation are non-interpretable, its predictions are considered as non-explainable [200].”
From A Review on Deep-Learning-Based Cyberbullying Detection (2023) · cites this paper as [200]
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126 · see citing works
The Internet of Things: A survey
Atzori, L., Iera, A., & Morabito, G. (2010) · Computer Networks · doi:10.1016/j.comnet.2010.05.010 · Cited by 15,613 · see citing works
A Brief Survey of Deep Reinforcement Learning
Arulkumaran, K., Deisenroth, M. P., Brundage, M., & Bharath, A. A. (2017) · arXiv · doi:10.48550/arxiv.1708.05866 · Cited by 4,733 · see citing works
Deep Reinforcement Learning: A Brief Survey
Arulkumaran, K., Deisenroth, M. P., Brundage, M., & Bharath, A. A. (2017) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2743240 · Cited by 4,733 · see citing works
Deep Learning: Methods and Applications
Deng, L., & Yu, D. (2014) · Foundations and Trends® in Signal Processing · doi:10.1561/2000000039 · Cited by 3,480 · see citing works
Distilling Free-Form Natural Laws from Experimental Data
Schmidt, M., & Lipson, H. (2009) · Science · doi:10.1126/science.1165893 · Cited by 3,327 · see citing works
A survey of deep neural network architectures and their applications
Liu, W., Wang, Z., Liu, X., Zeng, N., Liu, Y., & Alsaadi, F. E. (2017) · Neurocomputing · doi:10.1016/j.neucom.2016.12.038 · Cited by 3,239 · see citing works
A survey on deep learning for big data
Zhang, Q., Yang, L. T., Chen, Z., & Li, P. (2018) · Information Fusion · doi:10.1016/j.inffus.2017.10.006 · Cited by 1,226 · see citing works
Miikkulainen, R. P., Liang, J., Meyerson, E., Rawal, A., Fink, D., Francon, O., Raju, B., Shahrzad, H., Navruzyan, A., Duffy, N., et al. (2018) · Elsevier eBooks · doi:10.1016/b978-0-12-815480-9.00015-3 · Cited by 854 · see citing works
(2009) · The MIT Press eBooks · doi:10.7551/mitpress/8029.001.0001 · Cited by 743 · see citing works
Applications of machine learning and rule induction
Pat Langley, B., & Simon, H. A. (1995) · Communications of the ACM · doi:10.1145/219717.219768 · Cited by 505 · see citing works
(2017) · Penn Carey Law Legal Scholarship Repository (University of Pennsylvania) · Cited by 228 · see citing works
Big Data, Data Mining, and Machine Learning
Dean, J. (2014) · Wiley eBooks · doi:10.1002/9781118691786 · Cited by 184 · see citing works
Artificial neural networks in accounting and finance: modeling issues
Coakley, J. R., & Brown, C. E. (2000) · Intelligent systems in accounting, finance and management/Intelligent systems in accounting, finance & management · doi:10.1002/1099-1174(200006)9:2 · Cited by 131 · see citing works
Artificial Intelligence and Machine Learning Algorithms
Tyagi, A. K., & Chahal, P. (2019) · Advances in computer and electrical engineering book series · doi:10.4018/978-1-7998-0182-5.ch008 · Cited by 76 · see citing works
Self-citationChallenges of Applying Deep Learning in Real-World Applications
Tyagi, A. K., & Rekha, G. (2019) · Advances in computer and electrical engineering book series · doi:10.4018/978-1-7998-0182-5.ch004 · Cited by 32 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
A Review on Deep-Learning-Based Cyberbullying Detection
Hasan, M. T., Hossain, M. A. E., Mukta, M. S. H., Akter, A., Ahmed, M., & Islam, S. (2023) · Future Internet · doi:10.3390/fi15050179 · Cited by 103 · see citing works
“Since DL’s hidden weight and activation are non-interpretable, its predictions are considered as non-explainable [200] In the present world, data are very dynamic.”
Background
- Authors
- Pramod, A., Naicker, H. S., & Tyagi, A. K.
- Affiliations
- Vellore Institute of Technology University (IN)
- Corresponding author
- Tyagi, Amit Kumar
- Venue
- Computational Analysis and Deep Learning for Medical Care
- Publisher
- Wiley
- Published
- 2021-07-28
- Pages
- 463-490
- OpenAlex
- W3194926994
- Cited by
- 85
- References
- 16
- Citations by year
- 2026: 5 · 2025: 33 · 2024: 19 · 2023: 15 · 2022: 10 · 2021: 3
- Type
- other
- Language
- en
- Open access
- closed
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Physical Sciences › Computer Science › Information Systems › Internet of Things and AI
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- Keywords
- machine learning, deep learning, machine learning applications, future research directions, e-health, disease detection, sound recognition, customer churn prediction, firm productivity
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
