Abstract
Not like many visual systems or NLP frameworks, human generally use both visual and semantic information for reasoning tasks. In this paper, we present a 3D virtual simulation learning environment Fuzzy World based on gradual learning paradigm to train visual-semantic reasoning agent for complex logic reasoning tasks. Furthermore our baseline approach employed semantic graphs and deep reinforcement learning architecture shows the significant performance over the tasks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Implemented at https://github.com/Luomin1993/fuzzy-world-tool.
References
Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. Artif. Intell. 101(1–2), 99–134 (1998)
Angluin, D.: Queries and concept learning. Mach. Learn. 2(4), 319–342 (1988)
Apt, K.R., Bol, R.N.: Logic programming and negation: a survey. J. Logic Program. 19(94), 9–71 (1994)
Apt, K.R., Emden, M.H.V.: Contributions to the theory of logic programming. J. ACM 29(3), 841–862 (1982)
Besold, T., et al.: Neural-symbolic learning and reasoning: a survey and interpretation
Chein, M., Mugnier, M.-L.: Graph-based knowledge representation: computational foundations of conceptual graphs. Univ. Aberdeen 13(3), 329–347 (2009)
Chen, D.L., Mooney, R.J.: Learning to interpret natural language navigation instructions from observations. In: AAAI Conference on Artificial Intelligence, AAAI 2011, San Francisco, California, USA (2011)
Chen, H., Suhr, A., Misra, D., Snavely, N., Artzi, Y.: Touchdown: natural language navigation and spatial reasoning in visual street environments
Chollet, F., et al.: Keras (2015). https://keras.io
Dai, W.Z., Xu, Q.L., Yu, Y., Zhou, Z.H.: Tunneling neural perception and logic reasoning through abductive learning
Das, A., Datta, S., Gkioxari, G., Lee, S., Parikh, D., Batra, D.: Embodied question answering. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (2018)
Duda, R., Gaschnig, J., Hart, P.: Model design in the prospector consultant system for mineral exploration. Read. Artif. Intell. 334–348 (1981)
Feigenbaum, E.A., Buchanan, B.G. Lederberg, J.: Generality and problem solving: a case study using the DENDRAL program. Stanford University (1970)
Frome, A., Corrado, G.S., Shlens, J., Bengio, S., Dean, J., Ranzato, M., Mikolov, T.: DeViSE: a deep visual-semantic embedding model. In: International Conference on Neural Information Processing Systems, pp. 2121–2129 (2013)
Gordon, D., Kembhavi, A., Rastegari, M., Redmon, J., Fox, D., Farhadi, A.: IQA: visual question answering in interactive environments
Hermann, K.M., Felix Hill, S.G., Fumin Wang, P.B.: Grounded language learning in a simulated 3D world. In: NIPS Workshop (2017)
Higgins, I., et al.: SCAN: learning abstract hierarchical compositional visual concepts
Mamdani, A.S.: An experiment in linguistic synthesis with a fuzzy logic controller. Int. J. Man-Mach. Stud. 7, 1–13 (1975)
Mccarthy, J.: Programs with common sense. Semant. Inf. Proces. 130(5), 403–418 (1959)
Mordatch, I.: Concept learning with energy-based models. In: ICLR Workshop (2018)
Ohlbach, H.J.: The semantic clause graph procedure - a first overview. In: Gwai-86 Und 2 Österreichische Artificial-intelligence-tagung (1986)
Regneri, M., Rohrbach, M., Wetzel, D., Thater, S., Pinkal, M.: Grounding action descriptions in videos. Trans. Assoc. Comput. Lingus 1(3), 25–36 (2013)
Shortliffe, E.H.: A rule-based computer program for advising physicians regarding antimicrobial therapy selection. Stanford University (1974)
Shridhar, M., et al.: ALFRED: a benchmark for interpreting grounded instructions for everyday tasks
Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., Mei, Q.: Line: large-scale information network embedding (2015)
Tellex, S., et al.: Understanding natural language commands for robotic navigation and mobile manipulation. In: AAAI Conference on Artificial Intelligence, pp. 1507–1514 (2011)
Tenenbaum, J.B.: Bayesian modeling of human concept learning. In: Conference on Advances in Neural Information Processing Systems II, pp. 59–65 (1998)
Torralba, X., et al.: VirtualHome: simulating household activities via programs. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (2018)
Watkins, C.J., Dayan, P.: Technical note: Q-learning. Mach. Learn. 8(3–4), 279–292 (1992)
Winograd, T.: Procedures as a representation for data in a computer program for understanding natural language. Technical report, Massachusetts Institute of Technology (1971)
Yu, H., Lian, X., Zhang, H., Xu, W.: Guided feature transformation (GFT): a neural language grounding module for embodied agents
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
1.1 6.1 Using Second Order Derivative Gradient for Cross Training Parameter
Notice that the prediction of the model \(\mathcal {P}(L_A|V, L_Q)\) is in one-hot form of space concept like:[up and down, left and right, top left and bottom right...], then the loss of last layer employed softmax cross entropy loss is \(\mathcal {L}(A_S) = -\hat{y} \odot log(f_{softmax}(A_S \odot C^{*T}))\). The next is the provement of an upper bound of \(\hat{\mathcal {L}}(A+ \alpha \varDelta A)\).
Note that the updating of parameters A takes the simple SGD: \( A^{t+1} \leftarrow A^t+\alpha \nabla _A \hat{\mathcal {L}} \).
Theorem 1
When \(\nabla ^2_A \hat{\mathcal {L}} \le MI\), we have\(\hat{\mathcal {L}}(A+ \alpha \varDelta A) \le \hat{\mathcal {L}}(A) + \gamma ||\nabla _A \hat{\mathcal {L}}||^2\).
Proof
Easy to know \(-\nabla _A \hat{\mathcal {L}}(A) = \varDelta A\), do Taylor expansion to \(\hat{\mathcal {L}}(A+ \alpha \varDelta A)\):
Now let \(\gamma = \alpha ^2M /2 - \alpha \le 0\) then the below is satisfied:
.
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Luo, M. (2021). Fuzzy World: A Tool Training Agent from Concept Cognitive to Logic Inference. In: Karlapalem, K., et al. Advances in Knowledge Discovery and Data Mining. PAKDD 2021. Lecture Notes in Computer Science(), vol 12712. Springer, Cham. https://doi.org/10.1007/978-3-030-75762-5_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-75762-5_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-75761-8
Online ISBN: 978-3-030-75762-5
eBook Packages: Computer ScienceComputer Science (R0)