Advancing Perception in Artificial Intelligence through Principles of Cognitive Science
Not on the map. Why?
Abstract (arXiv)
Although artificial intelligence (AI) has achieved many feats at a rapid pace, there still exist open problems and fundamental shortcomings related to performance and resource efficiency. Since AI researchers benchmark a significant proportion of performance standards through human intelligence, cognitive sciences-inspired AI is a promising domain of research. Studying cognitive science can provide a fresh perspective to building fundamental blocks in AI research, which can lead to improved performance and efficiency. In this review paper, we focus on the cognitive functions of perception, which is the process of taking signals from one's surroundings as input, and processing them to understand the environment. Particularly, we study and compare its various processes through the lens of both cognitive sciences and AI. Through this study, we review all current major theories from various sub-disciplines of cognitive science (specifically neuroscience, psychology and linguistics), and draw parallels with theories and techniques from current practices in AI. We, hence, present a detailed collection of methods in AI for researchers to build AI systems inspired by cognitive science. Further, through the process of reviewing the state of cognitive-inspired AI, we point out many gaps in the current state of AI (with respect to the performance of the human brain), and hence present potential directions for researchers to develop better perception systems in AI.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 85 of its 284 references that are in the map. First posted on arXiv 13 Oct 2023.
Builds on
85 of 284 references.
References · 85
- 2020Scaling Laws for Neural Language Modelscited by 6,411
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
- 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
- 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
- 2013Visualizing and Understanding Convolutional Networkscited by 2,278
- 2019Language Models as Knowledge Bases?cited by 1,922
- 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
- 2019A Comprehensive Survey on Transfer Learningcited by 1,154
- 2019BERT Rediscovers the Classical NLP Pipelinecited by 1,046
- 2022Diffusion Models in Vision: A Surveycited by 1,008
- 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 994
- 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
38 more
- 2023A Comprehensive Overview of Large Language Modelscited by 639
- 2022Towards Reasoning in Large Language Models: A Surveycited by 593
- 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 492
- 2023Augmented Language Models: a Surveycited by 398
- 2021Attention Bottlenecks for Multimodal Fusioncited by 361
- 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 256
- 2021Mind the Gap: Assessing Temporal Generalization in Neural Language Modelscited by 226
- 2021Charformer: Fast Character Transformers via Gradient-based Subword Tokenizationcited by 158
- 2022A Review on Language Models as Knowledge Basescited by 156
- 2021Between words and characters: A Brief History of Open-Vocabulary Modeling and Tokenization in NLPcited by 130
- 2020A Survey on Negative Transfercited by 120
- 2021Learning to Track with Object Permanencecited by 117
- 2017Natural Language Processing: State of The Art, Current Trends and Challengescited by 114
- 2022Navigating to Objects in the Real Worldcited by 104
- 2023Wider and Deeper LLM Networks are Fairer LLM Evaluatorscited by 91
- 2017Recent Advances in Recurrent Neural Networkscited by 89
- 2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
- 2020Fast WordPiece Tokenizationcited by 85
- 2022Surface Representation for Point Cloudscited by 84
- 2023Cognitive Mirage: A Review of Hallucinations in Large Language Modelscited by 83
- 2020The Case for Bayesian Deep Learningcited by 68
- 2016A Comprehensive Survey on Cross-modal Retrievalcited by 62
- 2019An Annotated Dataset of Coreference in English Literaturecited by 57
- 2023On the Creativity of Large Language Modelscited by 57
- 2022Dynamic Multimodal Fusioncited by 54
- 2023When Brain-inspired AI Meets AGIcited by 54
- 2022Shape-invariant 3D Adversarial Point Cloudscited by 49
- 2022Predictive Coding: Towards a Future of Deep Learning beyond Backpropagation?cited by 45
- 2023Entity Tracking in Language Modelscited by 44
- 2017Understanding Hidden Memories of Recurrent Neural Networkscited by 43
- 2023CORE: Cooperative Reconstruction for Multi-Agent Perceptioncited by 41
- 2014Scale-Invariant Convolutional Neural Networkscited by 40
- 2020Whence the Expected Free Energy?cited by 40
- 2019What Else Can Fool Deep Learning? Addressing Color Constancy Errors on Deep Neural Network Performancecited by 37
- 2023Emergent Modularity in Pre-trained Transformerscited by 37
- 2015Convolutional Color Constancycited by 36
- 2022SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detectioncited by 33
- 2023Are Multilingual LLMs Culturally-Diverse Reasoners? An Investigation into Multicultural Proverbs and Sayingscited by 32
50 most cited of 85 All 85 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.