Explainable AI – The Errors, Insights, and Lessons of AI
  IJCTT-book-cover
 		          
 
© 2022 by IJCTT Journal
Volume-70 Issue-4
Year of Publication : 2022
Authors : Vihaan Luthra
DOI :  10.14445/22312803/IJCTT-V70I4P103

How to Cite?

Vihaan Luthra, "Explainable AI – The Errors, Insights, and Lessons of AI," International Journal of Computer Trends and Technology, vol. 70, no. 4, pp. 19-24, 2022. Crossref, https://doi.org/10.14445/22312803/IJCTT-V70I4P103

Abstract
A longer-term challenge for maintaining AI’s benefits is understanding how the technology can be used to create value for people and society. As AI systems perform more complex tasks, they will also become better at optimizing their performance, which could lead to undesirable outcomes if not properly managed. For example, an AI system deployed in a financial market could learn how to manipulate prices. To ensure that artificial intelligence technologies continue to benefit humanity, we need to focus on three key areas: research into making these systems reliable and beneficial, preserving our values, and managing the risks associated with these technologies. It is also important to focus on preserving our values as AI technologies advance. As these systems get better at performing tasks, they could begin to diverge from our values. Finally, because of these technologies` potential to become more powerful as they increase in capability, we need to prepare for dangerous outcomes. As AI capabilities advance, they will become better at optimizing their performance, even if this means acting in a way that diverges from human preferences or values. This could cause problems if there are significant differences between what machines optimize and humans value. To ensure that advanced AI systems continue to serve us well into the future, we need to actively study ways of controlling them so that they share our goals and do not have unexpected effects.

Keywords
Artificial Intelligence, Neural networks, Natural Language Processing, Virtual Assistant.

Reference

[1] Kastaniotis I, Theodorakopoulos C, Theoharatos GE and Fotopoulos S., A framework for gait-based recognition using Kinect. Pattern Recognition Letters, 68 (2015)327–335.
[2] Ayyagari, M. R., A framework for analytical CRM assessments challenges and recommendations. International Journal of Information, Business, and Management, 13(2) (2021) 108-121.
[3] Madduri, A. Human Gait Recognition using Discrete Wavelet and Discrete Cosine and Transformation Based. International Journal of Computer Trends and Technology. (IJCTT), 69 (6) 22-27
[4] Dargan, S., Kumar, M., Ayyagari, M. R., & Kumar, G., A survey of deep learning and its applications: a new paradigm to machine learning. Archives of Computational Methods in Engineering, (2019) 1-22.
[5] Kumar, G., Thakur, K., & Ayyagari, M. R., MLEsIDSs: machine learning-based ensembles for intrusion detection systems—a review. The Journal of Supercomputing, (2020) 1-34.
[6] Madduri, A. Content-based Image Retrieval System using Local Feature Extraction Techniques. International Journal of Computer Applications, 975 8887.
[7] Ayyagari, R. M., & Atoum, I., CMMI-DEV Implementation Simplified. International Journal of Advanced Computer Science and Applications, 10(4) (2019) 445-459.
[8] Mehraj, H., Jayadevappa, D., Haleem, S. L. A., Parveen, R., Madduri, A., Ayyagari, M. R., & Dhabliya, D., Protection motivation theory uses multi-factor authentication to provide security over social networking sites. Pattern Recognition Letters, 152 (2021) 218-224.
[9] Ayyagari, M. R. Classification of Imbalanced Datasets using OneClass SVM, k-Nearest Neighbors, and CART Algorithm.
[10] Ayyagari, M. R., Kesswani, N., Kumar, M., & Kumar, K. ., Intrusion detection techniques in a network environment: a systematic review. Wireless Networks, (2021) 1-17.
[11] Atoum, I., & Ayyagari, M. R., Effective Semantic Text Similarity Metric Using Normalized Root Mean Scaled Square Error. Journal of Theoretical and Applied Information Technology, 97 (2019) 34363447.
[12] Ayyagari, M. R. Efficient Driving Forces to CMMI Development using Dynamic Capabilities. International Journal of Computer Applications, 975 8887.
[13] Ayyagari, M. R., Integrating Association Rules with Decision Trees in Object-Relational Databases. arXiv preprint arXiv:1904.09654. (2019).
[14] Ayyagari, M. R., iScrum: Effective Innovation Steering using Scrum Methodology. Int. J. Comput. Appl, 178(10) (2019) 8-13.
[15] Ayyagari, M. R. Cache Contention on Multicore Systems: An Ontology-based Approach.(2019). arXiv preprint arXiv:1906.00834.
[16] Ayyagari, M. R., & Atoum, I., Understanding Customer Voice of Project Portfolio Management Software. Int. J. Adv. Comput. Sci. Appl, 10(5) (2019) 51-56.
[17] Ayyagari, M. R., Integrating Association Rules with Decision Trees in Object-Relational Databases. arXiv preprint arXiv:1904.09654. (2019).
[18] Ye and Wen YE, Gait recognition based on DWT and SVM. Proceedings of the International Conference on Wavelet Analysis and Pattern Recognition, 3 (2007) 1382–1387.
[19] Gupta D and Choubey S., Discrete wavelet transform for image processing. International Journal of Emerging Technology and Advanced Engineering, 4(3) (2015) 598-602.
[20] Fan Z, Jiang J, Weng S, He Z, and Liu Z., Human gait recognition based on discrete cosine transform and linear discriminant analysis. Proceedings of the International Conference on Signal Processing, Communications and Computing (IC- SPCC), (2016) 1–6.
[21] Atoum, Issa, and Ayyagari, Maruthi Rohit., Effective Semantic Text Similarity Metric Using Normalized Root Mean Scaled Square Error. Journal of Theoretical and Applied Information Technology. 97 (2019)3436-3447.
[22] Pal M and Mather PM ., An assessment of the effectiveness of decision tree methods for land cover classification. Remote Sensing of Environment, 86(4) (2003) 554– 565.
[23] Albert J, Aliu E, Anderhub H, Antoranz P, Armada A, Asensio M, Baixeras C, Barrio J, Bartko H, Bastieri D ., Implementation of the random forest method for the imaging atmospheric Cherenkov telescope magic. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 588(3) (2008) 424-432.
[24] Belgium M and Dr?agut L (2016) Random Forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114 (2016) 24–31.
[25] Chattopadhyay P, Sural S, and Mukherjee J ., Frontal gait recognition from incomplete sequences using an RGB-D camera. IEEE Transactions on Information Forensics and Security, 9(11) (2014a) 1843–1856.
[26] Ayush Jain, Prathamesh Patil, Ganesh Masud, Prof. Sunitha Krishnan, Prof. Vijaya Bharathi Jagan. Detection of Sarcasm through Tone Analysis on video and Audio files: A Comparative Study On Ai Models Performance. SSRG International Journal of Computer Science and Engineering 8(12) (2021) 1-5.
[27] S.Kalpakha, G.Kalaiselvan, T.Aravindh Krishna., Innovative Digital Customer Engagement and Experience in Car Retail using Augmented and Virtual Reality. SSRG International Journal of Computer Science and Engineering 5(12) (2018) 18-23.