mlsanityData to 7 Oct 2026

A Whole Brain Probabilistic Generative Model: Toward Realizing Cognitive Architectures for Developmental Robots

arXiv 2103.08183 ↗First posted 15 Mar 2021cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Building a humanlike integrative artificial cognitive system, that is, an artificial general intelligence (AGI), is the holy grail of the artificial intelligence (AI) field. Furthermore, a computational model that enables an artificial system to achieve cognitive development will be an excellent reference for brain and cognitive science. This paper describes an approach to develop a cognitive architecture by integrating elemental cognitive modules to enable the training of the modules as a whole. This approach is based on two ideas: (1) brain-inspired AI, learning human brain architecture to build human-level intelligence, and (2) a probabilistic generative model(PGM)-based cognitive system to develop a cognitive system for developmental robots by integrating PGMs. The development framework is called a whole brain PGM (WB-PGM), which differs fundamentally from existing cognitive architectures in that it can learn continuously through a system based on sensory-motor information. In this study, we describe the rationale of WB-PGM, the current status of PGM-based elemental cognitive modules, their relationship with the human brain, the approach to the integration of the cognitive modules, and future challenges. Our findings can serve as a reference for brain studies. As PGMs describe explicit informational relationships between variables, this description provides interpretable guidance from computational sciences to brain science. By providing such information, researchers in neuroscience can provide feedback to researchers in AI and robotics on what the current models lack with reference to the brain. Further, it can facilitate collaboration among researchers in neuro-cognitive sciences as well as AI and robotics.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 47 of its 188 references that are in the map. First posted on arXiv 15 Mar 2021.

Builds on

47 of 188 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  6. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  7. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  8. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  9. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
  10. 2020Mastering Atari with Discrete World Modelscited by 990
  11. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  12. 2018Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Reviewcited by 466
35 more
  1. 2016The Option-Critic Architecturecited by 433
  2. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 388
  3. 2018Pyro: Deep Universal Probabilistic Programmingcited by 379
  4. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 359
  5. 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
  6. 2016Attend, Infer, Repeat: Fast Scene Understanding with Generative Modelscited by 209
  7. 2018Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objectscited by 128
  8. 2016Joint Multimodal Learning with Deep Generative Modelscited by 87
  9. 2020Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstructioncited by 66
  10. 2019Shaping Belief States with Generative Environment Models for RLcited by 65
  11. 2020Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challengecited by 55
  12. 2019Variational Recurrent Models for Solving Partially Observable Control Taskscited by 46
  13. 2018Cognitive computational neurosciencecited by 43
  14. 2020On the Relationship Between Active Inference and Control as Inferencecited by 42
  15. 2019A free energy principle for a particular physicscited by 40
  16. 2018Symbol Emergence in Cognitive Developmental Systems: a Surveycited by 39
  17. 2019Variational Inference MPC for Bayesian Model-based Reinforcement Learningcited by 39
  18. 2016Very Deep Convolutional Networks for End-to-End Speech Recognitioncited by 34
  19. 2015Symbol Emergence in Robotics: A Surveycited by 31
  20. 2017Deep Probabilistic Programmingcited by 24
  21. 2020PlaNet of the Bayesians: Reconsidering and Improving Deep Planning Network by Incorporating Bayesian Inferencecited by 22
  22. 2019Neuro-SERKET: Development of Integrative Cognitive System through the Composition of Deep Probabilistic Generative Modelscited by 20
  23. 2017SERKET: An Architecture for Connecting Stochastic Models to Realize a Large-Scale Cognitive Modelcited by 15
  24. 2018Improved and Scalable Online Learning of Spatial Concepts and Language Models with Mappingcited by 13
  25. 2021Predictive Processing in Cognitive Robotics: a Reviewcited by 13
  26. 2017Online Spatial Concept and Lexical Acquisition with Simultaneous Localization and Mappingcited by 10
  27. 2020Spatial Concept-Based Navigation with Human Speech Instructions via Probabilistic Inference on Bayesian Generative Modelcited by 9
  28. 2015Nonparametric Bayesian Double Articulation Analyzer for Direct Language Acquisition from Continuous Speech Signalscited by 6
  29. 2016Spatial Concept Acquisition for a Mobile Robot that Integrates Self-Localization and Unsupervised Word Discovery from Spoken Sentencescited by 6
  30. 2020Autonomous Planning Based on Spatial Concepts to Tidy Up Home Environments with Service Robotscited by 6
  31. 2020DREAM Architecture: a Developmental Approach to Open-Ended Learning in Roboticscited by 5
  32. 2021The whole brain architecture approach: Accelerating the development of artificial general intelligence by referring to the braincited by 5
  33. 2021Hippocampal formation-inspired probabilistic generative modelcited by 5
  34. 2019Self-organization of action hierarchy and compositionality by reinforcement learning with recurrent neural networkscited by 4
  35. 2020lamBERT: Language and Action Learning Using Multimodal BERTcited by 3

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3.

4 papers.

  1. 2023World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challengescited by 35
  2. 2023Score Mismatching for Generative Modelingcited by 7
  3. 2023Rethinking the Evaluating Framework for Natural Language Understanding in AI Systems: Language Acquisition as a Core for Future Metricscited by 2
  4. 2022Brain-inspired probabilistic generative model for double articulation analysis of spoken languagecited by 0