A Comprehensive Explainable Framework for Designing Enhanced Deep Learning Models
DOI:
https://doi.org/10.53819/81018102t3086Abstract
Many deep learning models that show improved efficacy over current state-of-the-art models are built using ad-hoc design strategies. In this study, a framework was developed to enhance the explainability of deep learning models. The framework systematically explains each step involved in enhancing existing models so that users can understand, replicate and trust them. A design science research methodology was used to develop the framework to identify ambiguities and knowledge gaps in current approaches. Experimentation enhanced current deep learning models. The results of this study revealed that enhancing state-of-the-art deep learning models for prediction is made possible by using the suggested framework. Furthermore, the steps to achieve this are easy to comprehend. The main contribution of this study is the design of an explainable deep learning framework using a repeatable and understandable strategy that researchers can follow for improving state-of-the-art prediction models.
Keywords: Artificial intelligence ethics, time series prediction, irregular sequential patterns, machine learning models and deep learning framework.
References
A¨ıvodji, U., Arai, H., Fortineau, O., Gambs,S., Hara, S., and Tapp, A., (2019). Fairwashing: the risk of rationalization, Proceedings of the 36th International Conference Machine Learning Research, vol. 97, 161–170.
Alkhatib, A. and Bernstein, M. (2019). Street-level algorithms: A theory at the gaps between policy and decisions, Proceedings of Conference on Human Factors in Computing Systems, Glasgow, UK, 1-13.
Arrieta, A. B., Rodr´ıguez, N. D., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garc´ıa, S. , Gil-Lopez, S., Molina, D., Benjamins, R. , Chatila, R.. and Herrera, F.(2020). Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI, Information Fusion, vol. 58, 82–115.
Azlan, A., Yusof, Y., and Mohsin, M. F. M., (2019). Determining the impact of window length on time series forecasting using deep learning, International Journal of Advanced Computer Research, vol. 9, no. 44, pp. 260– 267.
Bai S., and Koltun, J. Z. K. V. (2019), Deep equilibrium models,” 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), (Vancouver), pp. 1–16.
Cerqueira, V., Torgo, L., and Soares, C., (2019). Machine learning vs statistical methods for time series forecasting: Size matters, arXiv:1909.13316, vol. [stat.ML], 1–9.
Chalvatzisa, C., and Hristu-Varsakelis, D. (2018). High-performance stock index trading: making effective use of a deep long short-term memory network, arXiv:1902.03125, vol. [q-fin.ST], pp. 1–30.
Chang, Y.-Y., Sun, F.-Y., Wu, Y.-H., and Lin, S.-D., (2018). A memory-network based solution for multivariate time-series forecasting, Association for the Advancement of Artificial Intelligence, vol. [cs.LG], 1–8.
Dandajena, K., Venter, I. M., Ghaziasgar, M., and Dodds, R, (2020). Complex sequential data analysis: A systematic literature review of existing algorithms, Conference of the South African Institute of Computer Scientists and Information Technologists 2020, (Cape Town), pp. 44–50, 2020.
Dandajena, K., Venter, I. M., Ghaziasgar, M., and Dodds, R., (2021). Selecting datasets for evaluating an enhanced deep learning framework, SATNAC 2021, (Drakensberg, Natal), pp. 1–7, 2021.
Dawson, D., Schleiger, E., Horton, J., McLaughlin, J., Robinson, C., Quezada, G., Scowcroft, J. and Hajkowicz, S., (2019). Artificial intelligence: Australia’s ethics framework, CSIRO, Australia, Tech. Rep.
Dignum, V. (2018). Ethics in artificial intelligence: introduction to the special issue, Ethics and Information Technology, vol. 20, 1–3.
Dignum,V. (2017). Responsible autonomy, Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI-17), Macao, 4698–4704.
Glenski, M., Weninger, T., and Volkova, V., (2019). Improved forecasting of cryptocurrency price using social signals, arXiv:1907.00558, vol. [q-fin.ST], pp. 1–11.
Gonen, H. and Goldberg, Y. (2019). Lipstick on a pig: Debiasing methods cover up systematic gender biases in word embeddings but do not remove them, Conference of the North American Chapter of the Association for Computer Linguistics, vol. 1, Minneapolis, MN, 609–614.
Grand View Research, (2022). Market Analysis Report, Grand View Research, Tech. Rep.
Hagendorff, T. (2020). The ethics of AI ethics—an evaluation of guidelines, Minds and Machines, vol. 30, no. 1, 99–120.
Huang, S., Wang, D., Wu, X. and Tang, A. (2019). DSANet: Dual self-attention network for multivariate time series forecasting, CIKM ’19: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, (Beijing), pp. 2129–2132, ACM.
Kearns, M. J., Roth, A., and Sharifi-Malvajerdi, S., (2019). Average individual fairness: Algorithms, generalization and experiments, arXiv:1905.10607, vol. [CoRR], 1–46.
Kuleshov,V., Fenner, N., and Ermon, S. (2018). Accurate uncertainties for deep learning using calibrated regression, Proceedings of the 35th International Conference Machine Learning Research, Stockholm, Sweden, vol. 80, 1–9.
Liu, J., Zhang, T., Han, G., and Gou, Y., (2018). TD-LSTM: Temporal dependencebased LSTM networks for marine temperature prediction, Sensors, vol. 18, no. 3697, pp. 1–13.
Maggiolo, M., and Spanakis, G., (2019). Autoregressive convolutional recurrent neural network for univariate and multivariate time series prediction, arXiv:1903.02540, vol. [cs.LG], pp. 1–8.
Makinen,M., Kanniainen, J. Gabbouj, M., and Iosifidis, A., (2018), Forecasting of jump arrivals in stock prices: New attention-based network architecture using limit order book data,” arXiv:1810.10845, vol. [q-fin.TR], pp. 1–29.
Mihaita, A. S., He, H. Li, Z., and Rizoiu, M.-A., (2018). Motorway traffic flow prediction using advanced deep learning, arXiv:1907.06356, vol. [cs.LG], pp. 1–10.
Philippe, E., and Carlos, A., (2012). Time-series data mining, ACM Computing Surveys, vol. 45, 18–26.
Qin,H. (2019). Comparison of deep learning models on time series forecasting: a case study of dissolved oxygen prediction, arXiv:1911.08414, vol. [eess.SP], pp. 1–16.
Romanov, A., De-Arteaga, M., Wallach, H. M., Chayes, J. T., Borgs, C., Chouldechova, A. , Geyik, S. C., Kenthapadi, K., Rumshisky, A., and Kalai, A. T. (2019). What’s in a name? Reducing bias in bios without access to protected attributes, Conference of the North American Chapter of the Association for Computer Linguistics, Mineapolis, MN, 1–10.
Salujaa, R. Malhi, A., Knapiˇc, S., Fr¨amling, K., and Cavdar, C. (2019). Towards a rigorous evaluation of explainability for multivariate.
Sardelicha, M., and Manandhar, S., (2018). Multimodal deep learning for short term stock volatility prediction. arXiv:1812.10479, vol. [q-fin.ST], pp. 1– 40.
Schwab, K. (2017). The Fourth Industrial Revolution. New York, NY: Crown Business, 2017.
Sepp¨al¨a, A. Birkstedt, T., and M¨antym¨aki, M. (2021). From ethical AI principles to governed AI, 42nd International Conference on Information Systems, Austin, TX, 1–18.
Siau, K. and Wang, W. (2020). Artificial intelligence (AI) ethics: Ethics of AI and ethical, Journal of Database Management, vol. 31, no. 2, 74–87.
Suresh, J. and Guttag, V. J. (2021). A framework for understanding sources of harm throughout the machine learning life cycle, Equity and Access in Algorithms, Mechanisms, and Optimization ’21, NY, USA, 1-9.
Thamik, H., and Wu, J., (2022). The impact of artificial intelligence on sustainable development in electronic markets, Sustainability, vol. 14, no. 7, 1–20.
Venable, J.R, Pries-Heje,J and Baskerville, R.L, (2017). Choosing a design science research methodology, Australasian Conference on Information Systems (ACIS) 2017 Proceedings, pp. 1–12.
Whittlestone, J., Nyrup, J., Alexandrova, A., and Cave, S. (2019). The role and limits of principles in ai ethics: Towards a focus on tensions, Proceedings of the Conference on AI, Ethics, and Society (AIES ’19), Honolulu, HI, 195–200.
Xu, F., Uszkoreit, H., Du, Y., Fan, W., Zhao, D., and Zhu, J. (2019). Explainable AI: A brief survey on history, research areas, approaches and challenges, Natural Language Processing and Chinese Computing, Dalian, China, 563–57.
Zhou, F., Zhou, H. M., Yang, Z. and Yang, L. (2019). EMD2FNN: A strategy combining empirical mode decomposition and factorization machine based neural network for stock market trend prediction, Expert Systems with Applications, vol. 115.
Downloads
Published
Versions
- 2023-06-20 (3)
- 2023-06-13 (2)
- 2023-06-13 (1)
