Abstract
The field of AI is rich in scientific and technical challenges. Progress needs to be made in machine learning paradigms to make them more efficient and less data intensive. Bridges between data-based and model-based AI are needed in order to benefit from the best of both approaches. Many real-life situations cannot yet be addressed by current robots, demanding progress in perception, scene interpretation or group coordination. This chapter addresses some of the major scientific and technological challenges in core AI technology.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The Integrative AI research challenge is beyond and not only a matter of software engineering, i.e., of putting together different components based on different AI representations and techniques. Notice that we do not mean that software engineering is a minor issue for the development of AI systems, especially from the point of view of democratization. An interesting question is what new fundamental research questions in software engineering are motivated by AI systems.
- 2.
tag cloud for our project DeFuseNN: https://defusenn.letstag.it/.
References
Muscettola, N., Nayak, P.P., Pell, B., Williams, B.C.: Remote agent: to boldly go where no AI system has gone before. Artif. Intell. 103(1–2), 5–47 (1998)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115(3), 211–252 (2015)
Gulshan, V., et al.: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316, 2402–2410 (2016)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Gori, M., Campiani, G., Rossi, A., Setacci, C.: The web of clinical data. J. Cardiovasc. Surg. 23, 717–718 (2014)
Melis, D.A., Jaakkola, T.: Towards robust interpretability with self-explaining neural networks. In: Advances in Neural Information Processing Systems, pp. 7775–7784 (2018)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
He, K., et al.: Deep residual learning for image recognition. CoRR abs/1512.03385, pp. 646–661 (2015)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)
Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12(7), 2121–2159 (2011)
Alex, G.: Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850 (2013)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Canziani, A., Paszke, A., Culurciello, E.: An analysis of deep neural network models for practical applications. arXiv preprint arXiv:1605.07678 (2016)
Bianco, S., et al.: Benchmark analysis of representative deep neural network architectures. IEEE Access 6, 64270–64277 (2018)
Devlin, J., et al.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Radford, A., et al.: Improving language understanding by generative pre-training, vol. 12 (2018)
Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683 (2019)
Brown, T.B., et al.: Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)
He, K., et al.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2020)
Misra, I., van der Maaten, L.: Self-supervised learning of pretext-invariant representations. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2020)
Chen, T., et al.: A simple framework for contrastive learning of visual representations. arXiv preprint arXiv:2002.05709 (2020)
Caron, M., et al.: Unsupervised learning of visual features by contrasting cluster assignments. arXiv preprint arXiv:2006.09882 (2020)
Tenorio, M.F., Wei-Tsih, L.: Self organizing neural networks for the identification problem. In: Advances in Neural Information Processing Systems (1989)
Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016)
Baker, B., et al.: Designing neural network architectures using reinforcement learning. arXiv preprint arXiv:1611.02167 (2016)
Zoph, B., et al.: Learning transferable architectures for scalable image recognition. CoRR abs/1707.07012. arXiv preprint arXiv:1707.07012 (2017)
Brock, A., et al.: Smash: one-shot model architecture search through hypernetworks. arXiv preprint arXiv:1708.05344 (2017)
Baker, B., et al.: Accelerating neural architecture search using performance prediction. arXiv preprint arXiv:1705.10823 (2017)
Elsken, T., Jan-Hendrik, M., Frank, H.: Simple and efficient architecture search for convolutional neural networks. arXiv preprint arXiv:1711.04528 (2017)
Pham, H., et al.: Efficient neural architecture search via parameter sharing. arXiv preprint arXiv:1802.03268 (2018)
Liu, H., Karen, S., Yiming, Y.: Darts: differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)
Erhan, D., et al.: Visualizing higher-layer features of a deep network. Univ. Montr. 1341(3), 1 (2009)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol. 8689. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_53
Xie, C., Wang, J., Zhang, Z., Ren, Z., Yuille, A.: Mitigating adversarial effects through randomization. In: International Conference on Learning Representations (2018)
Mahendran, A., Andrea, V.: Understanding deep image representations by inverting them. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)
Ballard, D.H.: Modular learning in neural networks. In: AAAI (1987)
Badrinarayanan, V., Handa, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling. arXiv preprint arXiv:1505.07293 (2015)
Thomee, B., et al.: The new data and new challenges in multimedia research. CoRR abs/1503.01817 (2015)
Strehl, A., Joydeep, G.: Cluster ensembles–-a knowledge reuse framework for combining multiple partitions. J. Mach. Learn. Res. 3, 583–617 (2002)
Krizhevsky, A., Ilya, S., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (2012)
Simonyan, K., Andrea, V., Andrew, Z.: Deep inside convolutional networks: visualising image classification models and saliency maps. In: Workshop at International Conference on Learning Representations (2014)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. CoRR, abs/1512.00567 (2015)
Montavon, G., Lapuschkin, S., Binder, A., Samek, W., Muller, K.-R.: Explaining nonlinear classification decisions with deep Taylor decomposition. Pattern Recognit. 65, 211–222 (2017)
Szegedy, C., et al.: Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)
Folz, J., et al.: Adversarial defense based on structure-to-signal autoencoders. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE (2020)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
Kurakin, A., Ian, G., Samy, B.: Adversarial examples in the physical world. arXiv preprint arXiv:1607.02533 (2016)
Carlini, N., David, W.: Towards evaluating the robustness of neural networks. In: 2017 IEEE Symposium on Security and Privacy (SP). IEEE (2017)
Yosinski, J., Clune, J., Nguyen, A., Fuchs, T., Lipson, H.: Understanding neural networks through deep visualization. arXiv preprint arXiv:1506.06579 (2015)
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)
Kumar, D., Taylor, G.W., Wong, A.: Opening the black box of financial ai with clear-trade: a class-enhanced attentive response approach for explaining and visualizing deep learning-driven stock market prediction. arXiv preprint arXiv:1709.01574 (2017)
Tishby, N., Zaslavsky, N.: Deep learning and the information bottleneck principle. In: 2015 IEEE Information Theory Workshop (ITW), pp. 1–5. IEEE (April 2015)
Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning requires rethinking generalization. arXiv preprint arXiv:1611.03530 (2016)
Siddiqui, S.A., Mercier, D., Munir, M., Dengel, A., Ahmed, S.: Tsviz: demystification of deep learning models for time-series analysis. IEEE Access 7, 67027–67040 (2019)
Saad, E.W., Wunsch II, D.C.: Neural network explanation using inversion. Neural Netw. 20(1), 78–93 (2007)
Andrews, R., Diederich, J., Tickle, A.B.: Survey and critique of techniques for extracting rules from trained artificial neural networks. Knowl.-Based Syst.8(6), 373–389 (1995)
Munir, M., Siddiqui, S.A., Küsters, F., Mercier, D., Dengel, A., Ahmed, S.: TSXplain: demystification of DNN decisions for time-series using natural language and statistical features. In: Tetko, I., Kůrková, V., Karpov, P., Theis, F. (eds.) Artificial Neural Networks and Machine Learning – ICANN 2019: Workshop and Special Sessions. ICANN 2019. Lecture Notes in Computer Science, vol. 11731. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30493-5_43
Davis, E., Marcus, G.: GPT-3, bloviator: OpenAI’s language generator has no idea what it’s talking about. MIT Technology Review (2020)
Etzioni, O., Li, M.: High-stakes AI decisions need to be automatically audited. WIRED (2019)
Weld, D., Bansal, G.: The challenge of crafting intelligible intelligence. Commun. ACM62(6), 70–79 (2019)
Fichte, J.K., Hecher, M., Szeider, S.: A time leap challenge for SAT-solving. In: Simonis, H. (ed.) Principles and Practice of Constraint Programming. CP 2020. Lecture Notes in Computer Science, vol. 12333. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58475-7_16
Palacio, S., Folz, J., Dengel, A., Hees, J., Raue, F.: What do deep learning networks like to see?. In: Proceedings CVPR 2018 International Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, USA (June 2018). https://arxiv.org/abs/1803.08337
Folz, J., Palacio, S., Hees, J., Dengel, A.: Adversarial defense based on structure-to-signal autoencoders. In: Proceedings WACV 2020, IEEE Winter Conference on Applications of Computer Vision, Aspen, Co, USA (March 2020). https://arxiv.org/abs/1803.07994
Floridi, L.: AI and its new winter: from myths to realities. Philos. Technol. 33, 1–3 (2020). https://doi.org/10.1007/s13347-020-00396-6
Shead, S.: Researchers: are we on the cusp of an ‘AI winter’?BBC News (2020). https://www.bbc.com/news/technology-51064369. Accessed 27 Nov 2020
McKenney, P.E. (ed.): Is parallel programming hard, and, if so, what can you do about it? (2017). https://www.kernel.org/pub/linux/kernel/people/paulmck/perfbook/perfbook.2017.01.02a.pdf
Gleixner, A., et al.: MIPLIB 2017: data-driven compilation of the 6th mixed-integer programming library. Mathematical Programming Computation (2020). (accepted for publication)
Bixby, R.: A brief history of linear and mixed-integer programming computation. Documenta Mathematica, Extra Volume: Optimization Stories, pp. 107–121 (2012)
Daugherty, P.R., Wilson, H.J.: Human+Machine: Reimagining Work in the Age of AI. Harvard Business Press, Boston (2018)
Travis, G.: How the Boeing 737 Max Disaster looks to a Software Developer. IEEE Spectrum, Piscataway (2019)
Hand, D.J., Khan, S.: Validating and verifying AI systems. Patterns 1(3), 100037 (2020)
Hutter, F, Kotthoff, L, Vanschoren, J. (eds.): Automated Machine Learning: Methods, Systems, Challenges. Springer, Heidelberg (2019). https://doi.org/10.1007/978-3-030-05318-5
Thornton, C., Hutter, F., Hoos, H.H., Leyton-Brown, K.: Auto-WEKA: combined selection and hyperparameter optimization of classification algorithms. In: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 847–855 (2013)
Hoos, H.H.: Automated algorithm configuration and parameter tuning. In: Hamadi, Y., Monfroy, E., Saubion, F. (eds.) Autonomous Search. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-21434-9_3
Blot, A., Hoos, H.H., Jourdan, L., Kessaci-Marmion, M.É., Trautmann, H.: MO-ParamILS: a multi-objective automatic algorithm configuration framework. In: Festa, P., Sellmann, M., Vanschoren, J. (eds.) Learning and Intelligent Optimization. LION 2016. Lecture Notes in Computer Science, vol. 10079. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-50349-3_3
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Dengel, A. et al. (2021). Next Big Challenges in Core AI Technology. In: Braunschweig, B., Ghallab, M. (eds) Reflections on Artificial Intelligence for Humanity. Lecture Notes in Computer Science(), vol 12600. Springer, Cham. https://doi.org/10.1007/978-3-030-69128-8_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-69128-8_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-69127-1
Online ISBN: 978-3-030-69128-8
eBook Packages: Computer ScienceComputer Science (R0)