A single computational model for many learning phenomena

Petrosino, Giancarlo; Parisi, Domenico

doi:10.1016/j.cogsys.2015.06.001

Cited by 1 publication

(1 citation statement)

References 29 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, if we end up with independent learning models for different cognitive/behavioural functions, we will be stuck again with another integration problem similar to the one discussed at the beginning of this section. Therefore, it is very important to achieve continuous autonomous development [25,35,36] in which the same system acquires one function after another from the very bottom up to high cognition. If this is realized with the integration of details on individual developmental events as referenced above, it will solve all the problems discussed so far.…”

Section: Introductionmentioning

confidence: 99%

Fusing autonomy and sociality via embodied emergence and development of behaviour and cognition from fetal period

Kuniyoshi

2019

Phil. Trans. R. Soc. B

View full text Add to dashboard Cite

Human-centred AI/Robotics are quickly becoming important. Their core claim is that AI systems or robots must be designed and work for the benefits of humans with no harm or uneasiness. It essentially requires the realization of autonomy, sociality and their fusion at all levels of system organization, even beyond programming or pre-training. The biologically inspired core principle of such a system is described as the emergence and development of embodied behaviour and cognition. The importance of embodiment, emergence and continuous autonomous development is explained in the context of developmental robotics and dynamical systems view of human development. We present a hypothetical early developmental scenario that fills in the very beginning part of the comprehensive scenarios proposed in developmental robotics. Then our model and experiments on emergent embodied behaviour are presented. They consist of chaotic maps embedded in sensory–motor loops and coupled via embodiment. Behaviours that are consistent with embodiment and adaptive to environmental structure emerge within a few seconds without any external reward or learning. Next, our model and experiments on human fetal development are presented. A precise musculo-skeletal fetal body model is placed in a uterus model. Driven by spinal nonlinear oscillator circuits coupled together via embodiment, somatosensory signals are evoked and learned by a model of the cerebral cortex with 2.6 million neurons and 5.3 billion synapses. The model acquired cortical representations of self–body and multi-modal sensory integration. This work is important because it models very early autonomous development in realistic detailed human embodiment. Finally, discussions toward human-like cognition are presented including other important factors such as motivation, emotion, internal organs and genetic factors. This article is part of the theme issue ‘From social brains to social robots: applying neurocognitive insights to human–robot interaction’.

show abstract

Section: Introductionmentioning

confidence: 99%

Fusing autonomy and sociality via embodied emergence and development of behaviour and cognition from fetal period

Kuniyoshi

2019

Phil. Trans. R. Soc. B

View full text Add to dashboard Cite

show abstract

A single computational model for many learning phenomena

Cited by 1 publication

References 29 publications

Fusing autonomy and sociality via embodied emergence and development of behaviour and cognition from fetal period

Fusing autonomy and sociality via embodied emergence and development of behaviour and cognition from fetal period

Contact Info

Product

Resources

About