Why deep neural nets cannot ever match biological intelligence and what to do about it?

Nikolić, Danko

doi:10.1007/s11633-017-1093-8

Cited by 15 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the one hand, we do not yet know what those principles are ( Mureşan 2004 ; Mureşan et al. 2005a ; Nikolić 2017 ). On the other hand, these principles have not presented themselves via any ab-initio simulation of physical or chemical processes in the nervous tissue, either.…”

Section: Introductionmentioning

confidence: 99%

The fractal brain: scale-invariance in structure and dynamics

et al. 2022

View full text Add to dashboard Cite

The past 40 years have witnessed extensive research on fractal structure and scale-free dynamics in the brain. Although considerable progress has been made, a comprehensive picture has yet to emerge, and needs further linking to a mechanistic account of brain function. Here, we review these concepts, connecting observations across different levels of organization, from both a structural and functional perspective. We argue that, paradoxically, the level of cortical circuits is the least understood from a structural point of view and perhaps the best studied from a dynamical one. We further link observations about scale-freeness and fractality with evidence that the environment provides constraints that may explain the usefulness of fractal structure and scale-free dynamics in the brain. Moreover, we discuss evidence that behavior exhibits scale-free properties, likely emerging from similarly organized brain dynamics, enabling an organism to thrive in an environment that shares the same organizational principles. Finally, we review the sparse evidence for and try to speculate on the functional consequences of fractality and scale-freeness for brain computation. These properties may endow the brain with computational capabilities that transcend current models of neural computation and could hold the key to unraveling how the brain constructs percepts and generates behavior.

show abstract

Section: Introductionmentioning

confidence: 99%

The fractal brain: scale-invariance in structure and dynamics

et al. 2022

View full text Add to dashboard Cite

show abstract

“…It is only the fast adaptive mechanisms that adjust the neural network directly. This results in a tri-level adaptive hierarchy, as proposed by the theory of practopoiesis (Nikolić 2015;2016;2017) (Figure 3D). This theory obtains empirical support in the present findings of the fast cleanup of afterimages and the slow learning of the cleanup skill.…”

Section: Discussionmentioning

confidence: 99%

Quickly fading afterimages: hierarchical adaptations in human perception

Klinger

Kell

Nikolić

2019

Preprint

Self Cite

View full text Add to dashboard Cite

Afterimages result from a prolonged exposure to still visual stimuli. They are best detectable when viewed against uniform backgrounds and can persist for multiple seconds. Consequently, the dynamics of afterimages appears to be slow by their very nature. To the contrary, we report here that about 50% of an afterimage intensity can be erased rapidly-within less than a second. The prerequisite is that subjects view a rich visual content to erase the afterimage; fast erasure of afterimages does not occur if subjects view a blank screen. Moreover, we find evidence that fast removal of afterimages is a skill learned with practice as our subjects were always more effective in cleaning up afterimages in later parts of the experiment. These results can be explained by a tri-level hierarchy of adaptive mechanisms, as has been proposed by the theory of practopoiesis.

show abstract

“…Additionally, according to [147], current DL techniques are insufficient for fixed network architectures. This is because recently introduced tri-traversal theory proves that DL techniques will need to adapt at three levels of organization (T3structure), that is, be equipped with intelligent procedures that rapidly adjust their network architectures, in order to deal with the complexity of the maritime environment as well as other contexts.…”

Section: B Existing Problems and Future Research Opportunitiesmentioning

confidence: 99%

A Comprehensive Survey of Prognostics and Health Management Based on Deep Learning for Autonomous Ships

et al. 2019

View full text Add to dashboard Cite

The maritime industry widely expects to have autonomous and semi-autonomous ships (autoships) in the near future. In order to operate and maintain complex and integrated systems in a safe, efficient and cost-beneficial manner, autoships will require intelligent Prognostics and Health Management (PHM) systems. Deep learning (DL) is a potential area for this development, as it is rapidly finding applications in a variety of domains, including self-driving cars, smartphones, vision systems, and more recently in PHM applications. This paper introduces and reviews four well-established DL techniques recently applied to various practical PHM problems. The purpose is to support creativity and provide inspiration towards PHM based on DL (PHMDL) in autoships and the maritime industry. This paper discusses benefits, challenges, suggestions, existing problems, and future research opportunities with respect to this significant new technology. Index Terms-Autonomous ships, deep learning, maritime industry, prognostics and health management.

show abstract

Why deep neural nets cannot ever match biological intelligence and what to do about it?

Cited by 15 publications

References 21 publications

The fractal brain: scale-invariance in structure and dynamics

The fractal brain: scale-invariance in structure and dynamics

Quickly fading afterimages: hierarchical adaptations in human perception

A Comprehensive Survey of Prognostics and Health Management Based on Deep Learning for Autonomous Ships

Contact Info

Product

Resources

About