Definition
Cascade–correlation (often abbreviated as “Cascor” or “CC”) is a supervised learning algorithm for artificial neural networks. It is related to the back-propagation algorithm (“backprop”). CC differs from backprop in that a CC network begins with no hidden units and then adds units one by one, as needed during learning.
Each new hidden unit is trained to correlate with residual error in the network built so far. When it is added to the network, the new unit is frozen, in the sense that its input weights are fixed. The hidden units form a cascade: each new unit receives weighted input from all the original network inputs and from the output of every previously created hidden unit. This cascading creates a network that is as deep as the number of hidden units. Stated another way, the CC algorithm is capable of efficiently creating complex, higher-order nonlinear basis functions – the hidden units – which are then combined to form the desired outputs.
The...
This is a preview of subscription content, log in via an institution to check access.
Recommended Reading
Baluja S, Fahlman SE (1994) Reducing network depth in the cascade-correlation learning architecture. School of Computer Science, Carnegie Mellon University, Pittsburgh
Buckingham D, Shultz TR (2000) The developmental course of distance, time, and velocity concepts: a generative connectionist model. J Cogn Dev 1:305–345
Dandurand F, Berthiaume V, Shultz TR (2007) A systematic comparison of flat and standard cascade-correlation using a student-teacher network approximation task. Connect Sci 19:223–244
Denison S, Xu F (2010) Twelve- to 14-month-old infants can predict single-event probability with large set sizes. Dev Sci 13(5):798–803
Denison S, Xu F (2014) The origins of probabilistic inference in human infants. Cognition 130(3):335–347
Denison S, Reed C, Xu F (2013) The emergence of probabilistic reasoning in very young infants: evidence from 4.5- and 6-month-olds. Dev Psychol 49(2):243–249
Fahlman SE (1988) Faster-learning variations on back-propagation: an empirical study. In: Touretzky DS, Hinton GE, Sejnowski TJ (eds) Proceedings of the 1988 connectionist models summer school. Morgan Kaufmann, Los Altos, pp 38–51
Fahlman SE (1991) The recurrent cascade-correlation architecture. In: Touretzky DS (ed) Advances in neural information processing systems, vol 3. Morgan Kaufmann, Los Altos
Fahlman SE, Lebiere C (1990) The cascade-correlation learning architecture. In: Touretzky DS (ed) Advances in neural information processing systems, vol 2. Morgan Kaufmann, Los Altos, pp 524–532
Gerken L, Balcomb F, Minton J (2011) Infants avoid “labouring in vain” by attending more to learnable than unlearnable linguistic patterns. Dev Sci 14(5):972–979
Justesen N, Bontrager P, Togelius J, Risi S (2019) Deep learning for video game playing. IEEE Trans on Games 12(1):1–20
Kharratzadeh M, Shultz T (2016) Neural implementation of probabilistic models of cognition. Cogn Syst Res 40:99–113
Mareschal D, Shultz TR (1999) Development of children’s seriation: a connectionist approach. Connect Sci 11:149–186
Marquez E, Hare J, Niranjan M (2018) Deep cascade learning. IEEE Trans Neural Networks Learn Syst 29(11):5475–5485
Nobandegani AS, Shultz TR (2017) Converting cascade-correlation neural nets into probabilistic generative models. Proceedings of the 39th Annual Meeting Cognitive Science Society, pp 1029–1034
Nobandegani AS, Shultz TR (2018) Example generation under constraints using cascade correlation neural nets. Proceedings of the 40th Annual Meeting Cognitive Science Society, pp 2385–2390
Oshima-Takane Y, Takane Y, Shultz TR (1999) The learning of first and second pronouns in English: network models and analysis. J Child Lang 26:545–575
Schlimm D, Shultz TR (2009) Learning the structure of abstract groups. In: Taatgen NA, Rijn HV (eds) Proceedings of the 31st annual conference of the cognitive science society. Cognitive Science Society, Austin, pp 2950–2955
Shultz TR (1998) A computational analysis of conservation. Dev Sci 1:103–126
Shultz TR (2003) Computational developmental psychology. MIT, Cambridge
Shultz TR (2006) Constructive learning in the modeling of psychological development. In: Munakata Y, Johnson MH (eds) Processes of change in brain and cognitive development: attention and performance XXI. Oxford University Press, Oxford, pp 61–86
Shultz TR, Bale AC (2006) Neural networks discover a near-identity relation to distinguish simple syntactic forms. Mind Mach 16:107–139
Shultz TR, Cohen LB (2004) Modeling age differences in infant category learning. Infancy 5:153–171
Shultz TR, Doty E (2014) Knowing when to quit on unlearnable problems: another step towards autonomous learning. In: Mayor J, Gomez P (eds) Computational models of cognitive processes. World Scientific, London, pp 211–221
Shultz TR, Nobandegani AS (2021) A computational model of infant learning and reasoning with probabilities. Psychol Rev. https://doi.org/10.1037/rev0000322
Shultz TR, Rivest F (2001) Knowledge-based cascade-correlation: using knowledge to speed learning. Connect Sci 13:1–30
Shultz TR, Takane Y (2007) Rule following and rule use in simulations of the balance-scale task. Cognition 103:460–472
Shultz TR, Vogel A (2004) A connectionist model of the development of transitivity. In: Proceedings of the twenty-sixth annual conference of the cognitive science society. Erlbaum, Mahwah, pp 1243–1248.
Shultz TR, Mareschal D, Schmidt WC (1994) Modeling cognitive development on balance scale phenomena. Mach Learn 16:57–86
Shultz TR, Rivest F, Egri L, Thivierge J-P, Dandurand F (2007) Could knowledge-based neural learning be useful in developmental robotics? The case of KBCC. Int J Humanoid Robot 4:245–279
Sirois S, Shultz TR (1998) Neural network modeling of developmental effects in discrimination shifts. J Exp Child Psychol 71:235–274
Xu F, Garcia V (2008) Intuitive statistics by 8-month-old infants. Proc Natl Acad Sci 105(13):5012–5015
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Science+Business Media, LLC, part of Springer Nature
About this entry
Cite this entry
Shultz, T.R., Nobandegani, A.S., Fahlman, S.E. (2022). Cascade–Correlation. In: Phung, D., Webb, G.I., Sammut, C. (eds) Encyclopedia of Machine Learning and Data Science. Springer, New York, NY. https://doi.org/10.1007/978-1-4899-7502-7_33-2
Download citation
DOI: https://doi.org/10.1007/978-1-4899-7502-7_33-2
Received:
Accepted:
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4899-7502-7
Online ISBN: 978-1-4899-7502-7
eBook Packages: Springer Reference Computer SciencesReference Module Computer Science and Engineering
Publish with us
Chapter history
-
Latest
Cascade–Correlation- Published:
- 27 April 2022
DOI: https://doi.org/10.1007/978-1-4899-7502-7_33-2
-
Original
Cascade-Correlation- Published:
- 17 February 2015
DOI: https://doi.org/10.1007/978-1-4899-7502-7_33-1