mlsanityData to 7 Oct 2026

The Construction of Reality in an AI: A Review

arXiv 2302.05448 ↗First posted 3 Feb 2023cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

AI constructivism as inspired by Jean Piaget, described and surveyed by Frank Guerin, and representatively implemented by Gary Drescher seeks to create algorithms and knowledge structures that enable agents to acquire, maintain, and apply a deep understanding of the environment through sensorimotor interactions. This paper aims to increase awareness of constructivist AI implementations to encourage greater progress toward enabling lifelong learning by machines. It builds on Guerin's 2008 "Learning Like a Baby: A Survey of AI approaches." After briefly recapitulating that survey, it summarizes subsequent progress by the Guerin referents, numerous works not covered by Guerin (or found in other surveys), and relevant efforts in related areas. The focus is on knowledge representations and learning algorithms that have been used in practice viewed through lenses of Piaget's schemas, adaptation processes, and staged development. The paper concludes with a preview of a simple framework for constructive AI being developed by the author that parses concepts from sensory input and stores them in a semantic memory network linked to episodic data. Extensive references are provided.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 34 of its 772 references that are in the map. First posted on arXiv 3 Feb 2023.

Builds on

34 of 772 references.

References · 34

  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  4. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,092
  5. 2018Progress & Compress: A scalable framework for continual learningcited by 516
  6. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  7. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  8. 2017A Brief Survey of Deep Reinforcement Learningcited by 466
  9. 2015LSTM: A Search Space Odysseycited by 315
  10. 2017One-Shot Imitation Learningcited by 232
  11. 2017Imagination-Augmented Agents for Deep Reinforcement Learningcited by 137
  12. 2017Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environmentscited by 106
22 more
  1. 2018Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactionscited by 100
  2. 2017Building machines that adapt and compute like brainscited by 99
  3. 2016Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learnercited by 68
  4. 2021The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalizationcited by 62
  5. 2017Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physicscited by 57
  6. 2019How Can We Be So Dense? The Benefits of Using Highly Sparse Representationscited by 45
  7. 2015Why Neurons Have Thousands of Synapses, A Theory of Sequence Memory in Neocortexcited by 44
  8. 2018Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programscited by 21
  9. 2017Teaching Compositionality to CNNscited by 18
  10. 2016Early Visual Concept Learning with Unsupervised Deep Learningcited by 16
  11. 2021Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Explorationcited by 14
  12. 2019Fixed-Horizon Temporal Difference Methods for Stable Reinforcement Learningcited by 12
  13. 2015Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Imagescited by 10
  14. 2017Understanding Early Word Learning in Situated Artificial Agentscited by 8
  15. 2018Unicorn: Continual Learning with a Universal, Off-policy Agentcited by 5
  16. 2019Learning to Crawlcited by 4
  17. 2021Hippocampal Spatial Mapping As Fast Graph Learningcited by 3
  18. 2016Balancing New Against Old Information: The Role of Surprise in Learningcited by 1
  19. 2018A Model for Auto-Programming for General Purposescited by 1
  20. 2019Towards Self-constructive Artificial Intelligence: Algorithmic basis (Part I)cited by 1
  21. 2019Should All Temporal Difference Learning Use Emphasis?cited by 1
  22. 2020A Model of Fast Concept Inference with Object-Factorized Cognitive Programscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023A Case for AI Safety via Lawcited by 0