Conclusions and Outlooks
- 235 Downloads
Capable of classifying huge amount of texts, translating hundreds of languages, predicting the rise and fall of global markets, even driving unmanned automobiles, Deep Learning systems are the hope of the fifth industrial revolution. However, recent studies have found that Deep Learning systems can be easily manipulated, i.e., in image recognition and in natural language understanding. The nature of one system of the mind (System 1), which Deep Learning systems simulates, dictates that any given data would be put into a coherent story, even at the cost of logic. Another system of the mind (System 2) manages logical thinking by following rules and structures, which symbolic AI simulates. How to combine Deep Learning with symbolic structures remains an open debate.
- Bauckhage, C., Schulz, D., & Hecker, D. (2019a). Informed Machine Learning for Industry. ERCIM News, 2019 (116).Google Scholar
- Bauckhage, C., Sifa, R., & Dong, T. (2019b). Prototypes within minimum enclosing balls. In ICANN-19 (pp. 365–376). Germany: Munich.Google Scholar
- Cremers, A. B., Thrun, S., & Burgard, W. (1994). From AI technology research to applications. In Proceedings of the IFIP Congress 94. Hamburg, Germany, Elsevier Science Publisher.Google Scholar
- Glasgow, J., Narayanan, N. H., & Chandrasekaran, B. (Eds.). (1995). Diagrammatic reasoning: Cognitive and computational perspectives. Cambridge, MA, USA: MIT Press.Google Scholar
- Grenon, P., & Smith, B. (2004). SNAP and SPAN: Towards dynamic spatial ontology. Spatial Cognition and Computation, 4(1), 69–103. Lawrence Erlbaum Associates, Inc.Google Scholar
- Lv, X., Hou, L., Li, J., & Liu, Z. (2018). Differentiating concepts and instances for knowledge graph embedding. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (pp. 1971–1979). Association for Computational Linguistics.Google Scholar
- Marcus, G. F. (2003). The algebraic mind–integrating connectionism and cognitive science. The MIT Press.Google Scholar
- Sun, R. (2016). Implicit and explicit processes: Their relation, interaction, and competition. In L. Macchi, M. Bagassi, & R. Viale (Eds.), Cognitive unconscious and human rationality (p. 257). Cambridge, MA: MIT Press.Google Scholar
- Tversky, B. (1993). Cognitive maps, cognitive collages, and spatial mental models. In A. Frank & I. Campari (Eds.), Spatial information theory—a theoretical basis for GIS (pp. 14–24). Springer.Google Scholar
- von Rüden, L., Mayer, S., Garcke, J., Bauckhage, C., & Schücker, J. (2019). Informed machine learning-towards a taxonomy of explicit integration of knowledge into machine learning. CoRR arXiv:abs/1903.12394.
- Whitehead, A. N. (1929). Process and reality. Macmillan Publishing Co., Inc.Google Scholar