Connectionism and Learning: Neural Networks Explained
This paper presents an annotated bibliography examining connectionism — a multidisciplinary cognitive science framework that models learning and mental processes through interconnected neural networks. Drawing on five peer-reviewed sources, the paper surveys the historical development of the Parallel Distributed Processing framework, the Causal Attitude Network (CAN) model, statistical learning in neural networks, connectionism's role in second language acquisition (SLA), and the implications of connectionist models for designing artificial moral agents. Together, these sources illustrate how researchers across psychology, linguistics, and artificial intelligence are converging on connectionism as a promising lens for understanding both human cognition and non-human intelligence.
- Introduction to Connectionism: Overview of connectionism and its multidisciplinary scope
- The History and Future of Connectionism (Mayor et al., 2014): PDP framework history and future learning challenges
- Attitudes as Neural Networks: The CAN Model (Dalege et al., 2016): CAN model explains attitudinal reactions via neural networks
- Statistical Learning and Neural Networks (Plaut & Vande Velde, 2017): Bayesian models and statistical learning in neural networks
- Connectionism and Second Language Acquisition (Nelson, 2013): Bilingual network models and biologically realistic connectionism
- Artificial Moral Agents and Connectionism (Wiltshire, 2015): Heroism and morality frameworks for AI neural networks
- Summary: Synthesis of five sources on connectionism's frontiers
✍️ How to write this paper — guide, tools & examples ▾
What makes this paper effective
- Each source is introduced with a clear rationale explaining why it was selected and how it connects to the broader topic of connectionism.
- The paper spans multiple disciplines — psychology, linguistics, AI ethics — demonstrating genuine breadth in surveying the field.
- Annotations move beyond simple description to highlight each source's contribution to understanding how neural networks model cognition.
Key academic technique demonstrated
The paper demonstrates the annotated bibliography format: each citation is followed by a concise critical annotation that summarizes the source's argument, methodology, and relevance to the overarching research theme. This technique helps readers quickly assess the scope and value of a body of literature.
Structure breakdown
The paper opens with a brief introduction that frames the topic and explains the author's interest in connectionism. Five annotated entries follow in a consistent pattern: citation, then annotation. A short summary paragraph closes the paper by synthesizing the collective significance of the five sources. The structure is appropriate for an undergraduate annotated bibliography assignment.
Introduction to Connectionism
This paper examines connectionism and its potential to model various learning processes in the brain through a multidisciplinary approach that combines many different theoretical frameworks — an approach that has recently received a significant boost from advances in technology. The basic principles of the connectionism model involve a sense of biological realism built upon interconnected networks that form a more complex whole, potentially explaining the processes within the human brain. These same principles may also serve as a foundation for developing non-human networks, such as artificial intelligence. Although it is not entirely clear how this research might be relevant to specific career goals at present, the field is developing so rapidly that knowledge of this subject could become highly relevant within the next five years.
The History and Future of Connectionism (Mayor et al., 2014)
Citation: Mayor, J., Gomez, P., Chang, F., & Lupyan, G. (2014). Connectionism coming of age: legacy and future challenges. Frontiers in Psychology. doi:10.3389/fpsyg.2014.00187
This article was chosen because it provides a rich and detailed history of how the connectionist model developed, as well as discussion of where the model could advance in the future. In 1986, Rumelhart and McClelland introduced the Parallel Distributed Processing (PDP) framework to the cognitive science community — a framework that sought to construct, at the algorithmic level, models of cognition compatible with their implementation in a biological substrate (Mayor, Gomez, Chang, & Lupyan, 2014). After reviewing the obstacles the theory has encountered, the article identifies its key challenge — learning abstract structural representations — and explains how many gaps must be filled before this model can fully account for complex intelligence.
Attitudes as Neural Networks: The CAN Model (Dalege et al., 2016)
Citation: Dalege, J., van den Berg, H., Borsboom, D., Conner, M., & van der Mas, H. (2016). Toward a formalized account of attitudes: The Causal Attitude Network (CAN) Model. Psychological Review, 2–21.
This article evaluates the ability of the CAN model to explain the reactions people have to events, as well as the interactions among those reactions. For example, when a person recoils at the sight of a snake, they are not engaging in a rational internal assessment of the threat; rather, they react based on their "attitude" toward snakes. Understanding how these attitudes are structurally represented in the brain's neural networks can begin to illuminate how such reactions manifest from a connectionist perspective and potentially open avenues for further study.
Works Cited
Dalege, J., van den Berg, H., Borsboom, D., Conner, M., & van der Mas, H. (2016). Toward a formalized account of attitudes: The Causal Attitude Network (CAN) Model. Psychological Review, 2–21.
Mayor, J., Gomez, P., Chang, F., & Lupyan, G. (2014). Connectionism coming of age: legacy and future challenges. Frontiers in Psychology. doi:10.3389/fpsyg.2014.00187
Nelson, R. (2013). Expanding the role of connectionism in SLA theory. Language Learning, 1–33.
Plaut, D., & Vande Velde, A. (2017). Statistical learning of parts and wholes: A neural network approach. Journal of Experimental Psychology, 318–336.
Wiltshire, T. (2015). A prospective framework for the design of ideal artificial moral agents: Insights from the science of heroism in humans. Minds and Machines, 57–71.
Always verify citation format against your institution’s current style guide requirements.