Abstract
The development of intelligent machines is one of the biggest unsolved challenges in computer science. In this paper, we propose some fundamental properties these machines should have, focusing in particular on communication and learning. We discuss a simple environment that could be used to incrementally teach a machine the basics of natural-language-based communication, as a prerequisite to more complex interaction with human users. We also present some conjectures on the sort of algorithms the machine should support in order to profitably learn from the environment.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ando, R., Zhang, T.: A framework for learning predictive structures from multiple tasks and unlabeled data. J. Mach. Learn. Res. 5, 1817–1853 (2005)
Artzi, Y., Zettlemoyer, L.: Weakly supervised learning of semantic parsers for mapping instructions to actions. Trans. Assoc. Comput. Linguist. 1(1), 49–62 (2013)
Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: Proceedings of ICML, Montreal, Canada, pp. 41–48 (2009)
Boleda, G., Erk, K.: Distributional semantic features as semantic primitives-or not. In: Proceedings of the AAAI Spring Symposium on Knowledge Representation and Reasoning: Integrating Symbolic and Neural Approaches, Stanford, CA, pp. 2–5 (2015)
Bottou, L.: From machine learning to machine reasoning: an essay. Mach. Learn. 94, 133–149 (2014)
Branavan, S., Silver, D., Barzilay, R.: Learning to win by reading manuals in a Monte-Carlo framework. J. Artif. Intell. Res. 43, 661–704 (2012)
Caruana, R.: Multitask learning. Mach. Learn. 28, 41–75 (1997)
Chen, D., Mooney, R.: Learning to interpret natural language navigation instructions from observations. In: Proceedings of AAAI, San Francisco, CA, pp. 859–865 (2011)
Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., Kuksa, P.: Natural language processing (almost) from scratch. J. Mach. Learn. Res. 12, 2493–2537 (2011)
Elman, J.: Learning and development in neural networks: the importance of starting small. Cognition 48, 71–99 (1993)
Erk, K.: Vector space models of word meaning and phrase meaning: a survey. Lang. Linguist. Compass 6(10), 635–653 (2012)
Fodor, J.: The Language of Thought. Crowell Press, New York (1975)
Geman, D., Geman, S., Hallonquist, N., Younes, L.: Visual turing test for computer vision systems. Proc. Natl. Acad. Sci. 112(12), 3618–3623 (2015)
Genesereth, M., Love, N., Pell, B.: General game playing: overview of the AAAI competition. AI Mag. 26(2), 62–72 (2005)
Graves, A., Wayne, G., Danihelka, I.: Neural turing machines (2014). http://arxiv.org/abs/1410.5401
Grefenstette, E., Hermann, K., Suleyman, M., Blunsom, P.: Learning to transduce with unbounded memory. In: Proceedings of NIPS, Montreal, Canada (2014) (in Press)
Haugeland, J.: Artificial Intelligence: The Very Idea. MIT Press, Cambridge (1985)
Joulin, A., Mikolov, T.: Inferring algorithmic patterns with stack-augmented recurrent nets. In: Proceedings of NIPS, Montreal, Canada (2015) (in Press)
Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. J. Artif. Intell. Res. 4, 237–285 (1996)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015)
Levesque, H.J., Davis, E., Morgenstern, L.: The Winograd schema challenge. In: Proceedings of KR, Rome, Italy, pp. 362–372 (2012)
Louwerse, M.: Symbol interdependency in symbolic and embodied cognition. Top. Cogn. Sci. 3, 273–302 (2011)
MacMahon, M., Stankiewicz, B., Kuipers, B.: Walk the talk: connecting language, knowledge, and action in route instructions. In: Proceedings of AAAI, Boston, MA, pp. 1475–1482 (2006)
Mikolov, T.: Incremental learning of algorithms. Unpublished manuscript (2013)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space (2013). http://arxiv.org/abs/1301.3781/
Mitchell, T., Cohen, W., Hruschka, E., Talukdar, P., Betteridge, J., Carlson, A., Mishra, B., Gardner, M., Kisiel, B., Krishnamurthy, J., Lao, N., Mazaitis, K., Mohamed, T., Nakashole, N., Platanios, E., Ritter, A., Samadi, M., Settles, B., Wang, R., Wijaya, D., Gupta, A., Chen, X., Saparov, A., Greaves, M., Welling, J.: Never-ending learning. In: Proceedings of AAAI, Austin, TX, pp. 2302–2310 (2015)
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A., Veness, J., Bellemare, M., Graves, A., Riedmiller, M., Fidjeland, A., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., Hassabis, D.: Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015)
Morelli, R., Brown, M., Anselmi, D., Haberlandt, K., Lloyd, D. (eds.): Minds, Brains, and Computers: Perspectives in Cognitive Science and Artificial Intelligence. Ablex, Norwood (1992)
Narasimhan, K., Kulkarni, T., Barzilay, R.: Language understanding for text-based games using deep reinforcement learning. In: Proceedings of EMNLP, Lisbon, Portugal, pp. 1–11 (2015)
Nwana, H.: Software agents: an overview. Knowl. Eng. Rev. 11(2), 1–40 (1996)
Poli, R., Langdon, W., McPhee, N., Koza, J.: A field guide to genetic programming (2008). http://www.gp-field-guide.org.uk
Prusinkiewicz, P., Lindenmayer, A.: The Algorithmic Beauty of Plants. Springer Science & Business Media, New York (2012)
Ring, M.: CHILD: a first step towards continual learning. Mach. Learn. 28, 77–104 (1997)
Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach, 3d edn. Pearson Education, New York (2009)
Schmidhuber, J.: Optimal ordered problem solver. Mach. Learn. 54(3), 211–254 (2004)
Schmidhuber, J.: On learning to think: algorithmic information theory for novel combinations of reinforcement learning controllers and recurrent neural world models (2015). http://arxiv.org/abs/1511.09249
Shoham, Y., Leyton-Brown, K.: Multiagent Systems. Cambridge University Press, Cambridge (2009)
Silver, D., Yang, Q., Li, L.: Lifelong machine learning systems: beyond learning algorithms. In: Proceedings of the AAAI Spring Symposium on Lifelong Machine Learning, Stanford, CA, pp. 49–55 (2013)
Solomonoff, R.J.: A formal theory of inductive inference. Part I. Inf. Control 7(1), 1–22 (1964)
Solomonoff, R.J.: The discovery of algorithmic probability. J. Comput. Syst. Sci. 55(1), 73–88 (1997)
Solomonoff, R.J.: Progress in incremental machine learning. In: NIPS Workshop on Universal Learning Algorithms and Optimal Search, Whistler, BC. Citeseer (2002)
Steels, L.: Social language learning. In: Tokoro, M., Steels, L. (eds.) The Future of Learning, pp. 133–162. IOS, Amsterdam (2003)
Steels, L.: What triggers the emergence of grammar? In: Proceedings of EELC, Hatfield, UK, pp. 143–150 (2005)
Sukhbaatar, S., Szlam, A., Synnaeve, G., Chintala, S., Fergus, R.: MazeBase: a sandbox for learning from games (2015). http://arxiv.org/abs/1511.07401
Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Tenenbaum, J.: Cognitive foundations for knowledge representation in AI. Presented at the AAAI Spring Symposium on Knowledge Representation and Reasoning (2015)
Thomason, J., Zhang, S., Mooney, R., Stone, P.: Learning to interpret natural language commands through human-robot dialog. Proceedings IJCAI, pp. 1923–1929. Buenos Aires, Argentina (2015)
Thrun, S., Pratt, L. (eds.): Learning to Learn. Kluwer, Dordrecht (1997)
Turing, A.: Computing machinery and intelligence. Mind 59, 433–460 (1950)
Turney, P., Pantel, P.: From frequency to meaning: vector space models of semantics. J. Artif. Intell. Res. 37, 141–188 (2010)
Von Neumann, J., Burks, A.W., et al.: Theory of self-reproducing automata. IEEE Trans. Neural Netw. 5(1), 3–14 (1966)
Weston, J., Bordes, A., Chopra, S., Mikolov, T.: Towards AI-complete question answering: a set of prerequisite toy tasks (2015). http://arxiv.org/abs/1502.05698
Wikipedia: Artificial human companion (2015a). https://en.wikipedia.org/w/index.php?title=Artificial_human_companion&oldid=685507143. Accessed 15 Oct 2015
Wikipedia: Interactive fiction (2015b). https://en.wikipedia.org/w/index.php?title=Interactive_fiction&oldid=693926750. Accessed 19 Dec 2015
Wikipedia: Turing test (2015c). https://en.wikipedia.org/w/index.php?title=Turing_test&oldid=673582926. Accessed 30 July 2015
Winograd, T.: Procedures as a representation for data in a computer program for understanding natural language. Technical report AI 235, Massachusetts Institute of Technology (1971)
Acknowledgments
We thank Léon Bottou, Yann LeCun, Gabriel Synnaeve, Arthur Szlam, Nicolas Usunier, Laurens van der Maaten, Wojciech Zaremba and others from the Facebook AI Research team, as well as Gemma Boleda, Katrin Erk, Germán Kruszewski, Angeliki Lazaridou, Louise McNally, Hinrich Schütze and Roberto Zamparelli for many stimulating discussions. An early version of this proposal has been discussed in several research groups since 2013 under the name Incremental learning of algorithms (Mikolov 2013).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Mikolov, T., Joulin, A., Baroni, M. (2018). A Roadmap Towards Machine Intelligence. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2016. Lecture Notes in Computer Science(), vol 9623. Springer, Cham. https://doi.org/10.1007/978-3-319-75477-2_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-75477-2_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-75476-5
Online ISBN: 978-3-319-75477-2
eBook Packages: Computer ScienceComputer Science (R0)