HexagDLy—Processing hexagonally sampled data with CNNs in PyTorch

Steppa, C.; Holch, T. L.

doi:10.1016/j.softx.2019.02.010

Cited by 42 publications

(45 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Turbo coding is further depicted as taking place between all four folded autoencoders (via an alpha complex, in blue), so instantiating further (hierarchical) turbo coding and thereby a larger shared latent space, so enabling predictive modeling of causes that achieve coherence via larger (and more slowly forming) modes of informational integration. This shared latent space is illustrated as containing an embedded graph neural network (GNN) Steppa and Holch, 2019), depicted as a hexagonal grid, as a means of integrating information via structured representations, where resulting predictions can then be propagated downward to individual folded autoencoders. Variable shading within the hexagonal grid-space of the GNN is meant to indicate degrees of recurrent activity-potentially implementing further turbo coding-and red arrows over this grid are meant to indicate sequences of activation, and potentially representations of trajectories through feature spaces.…”

Section: The Conscious Turbo-codementioning

confidence: 99%

Integrated World Modeling Theory (IWMT) Revisited

Safron¹

2019

Preprint

View full text Add to dashboard Cite

Here, I provide clarifications and discuss further issues relating to Safron (2020), “An Integrated World Modeling Theory (IWMT) of consciousness: Combining Integrated Information and Global Workspace Theories with the Free Energy Principle and Active Inference Framework; towards solving the Hard problem and characterizing agentic causation.” As a synthesis of major theories of complex systems and consciousness, with IWMT we may be able to address some of the most difficult problems in the sciences. This is a claim deserving of close scrutiny and much skepticism. What would it take to solve the Hard problem? One could answer the question of how it is possible that something like subjectivity could emerge from objective brain functioning (i.e., moving from a third person to a first person ontology), but a truly satisfying account might still require solving all the “easy” and “real” problems of consciousness. In this way, IWMT does not claim to definitively solve the Hard problem, as explaining all the particular ways that things feel across all relevant aspects of experience is likely an impossible task. Nonetheless, IWMT does claim to have made major inroads into our understanding of consciousness, and here I will attempt to justify this position by discussing challenging problems and outstanding questions with respect to philosophy, (neuro)phenomenology, computational principles, practical applications, and implications for existing theories of mind and life.

show abstract

Section: The Conscious Turbo-codementioning

confidence: 99%

Integrated World Modeling Theory (IWMT) Revisited

Safron¹

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…As the amount of research which combines principles from hexagonal image processing and machine learning is quite limited, this contribution also aims to overcome the downsides of currently developed hexagonal machine learning approaches. These include not only the development of hexagonal convolutional layers following Hoogeboom et al (2018) [25] and Steppa and Holch (2019) [26], but also the implementation of the underlying addressing scheme as well as the necessary processing steps for transformation and visualization.…”

Section: A Related Workmentioning

confidence: 99%

“…1) Convolutional layer: Current research by Steppa and Holch [26] suggest a hexagonal convolutional layer implementation where each hexagonal block of pixels is separated by a number of d /2 vertical slices with d denoting the horizontal diameter of the hexagonal pixel block. These hexagonal subblocks are then convolved using d convolutions with their respective kernels.…”

Section: A Hexagonal Layersmentioning

confidence: 99%

Hexagonal Image Processing in the Context of Machine Learning: Conception of a Biologically Inspired Hexagonal Deep Learning Framework

Schlosser

Friedrich

Kowerko

2019

2019 18th IEEE International Conference on Machine Learning and Applications (ICMLA)

View full text Add to dashboard Cite

Inspired by the human visual perception system, hexagonal image processing in the context of machine learning deals with the development of image processing systems that combine the advantages of evolutionary motivated structures based on biological models. While conventional state of the art image processing systems of recording and output devices almost exclusively utilize square arranged methods, their hexagonal counterparts offer a number of key advantages that can benefit both researchers and users. This contribution serves as a general application-oriented approach with the synthesis of the therefor designed hexagonal image processing framework, called Hexnet, the processing steps of hexagonal image transformation, and dependent methods. The results of our created test environment show that the realized framework surpasses current approaches of hexagonal image processing systems, while hexagonal artificial neural networks can benefit from the implemented hexagonal architecture. As hexagonal lattice format based deep neural networks, also called H-DNN, can be compared to their square counterpart by transforming classical square lattice based data sets into their hexagonal representation, they can also result in a reduction of trainable parameters as well as result in increased training and test rates.

show abstract

“…Turbo coding is further depicted as taking place between all four folded autoencoders (via an alpha complex, in blue), so instantiating further (hierarchical) turbo coding and thereby a larger shared latent space, so enabling predictive modeling of causes that achieve coherence via larger (and more slowly forming) modes of informational integration. This shared latent space is illustrated as containing an embedded graph neural network (GNN) (Liu et al, 2019;Steppa and Holch, 2019), depicted as a hexagonal grid, as a means of integrating information via structured representations, where resulting predictions can then be propagated downward to individual folded autoencoders. Variable shading within the hexagonal grid-space of the GNN is meant to indicate degrees of recurrent activitypotentially implementing further turbo coding-and red arrows over this grid are meant to indicate sequences of activation, and potentially representations of trajectories through feature spaces.…”

Section: Repeat Steps 3 and 4 Until Loopy Belief Propagation Convergesmentioning

confidence: 99%

An Integrated World Modeling Theory (IWMT) of consciousness: Combining Integrated Information and Global Neuronal Workspace Theories with the Free Energy Principle and Active Inference Framework; towards solving the Hard problem and characterizing agentic causation

Safron¹

2019

Preprint

View full text Add to dashboard Cite

The Free Energy Principle and Active Inference Framework (FEP-AI) begins with the understanding that persisting systems must regulate environmental exchanges and prevent entropic accumulation. In FEP-AI, minds and brains are predictive controllers for autonomous systems, where action-driven perception is realized as probabilistic inference. Integrated Information Theory (IIT) begins with considering the preconditions for a system to intrinsically exist, as well as axioms regarding the nature of consciousness. IIT has produced controversy because of its surprising entailments: quasi-panpsychism; subjectivity without referents or dynamics; and the possibility of fully-intelligent-yet-unconscious brain simulations. Here, I describe how these controversies might be resolved by integrating IIT with FEP-AI, where integrated information only entails consciousness for systems with perspectival reference frames capable of generating models with spatial, temporal, and causal coherence for self and world. Without that connection with external reality, systems could have arbitrarily high amounts of integrated information, but nonetheless would not entail subjective experience. I further describe how an integration of these frameworks may contribute to their evolution as unified systems theories and models of emergent causation. Then, inspired by both Global Neuronal Workspace Theory (GNWT) and the Harmonic Brain Modes framework, I describe how streams of consciousness may emerge as an evolving generation of sensorimotor predictions, with the precise composition of experiences depending on the integration abilities of synchronous complexes as self-organizing harmonic modes (SOHMs). These integrating dynamics may be particularly likely to occur via richly connected subnetworks affording body-centric sources of phenomenal binding and executive control. Along these connectivity backbones, SOHMs are proposed to implement loopy message passing (cf. turbo-codes) over predictive (autoencoding) networks, so generating maximum a posteriori estimates as coherent vectors governing neural evolution, with alpha frequencies generating basic awareness, and cross-frequency phase-coupling within theta frequencies for access consciousness and volitional control. These dynamic cores of integrated information also function as global workspaces, centered on posterior cortices, but capable of being entrained with frontal cortices and interoceptive hierarchies, so affording agentic causation. Integrated World Modeling Theory (IWMT) represents a synthetic approach to understanding minds that reveals compatibility between leading theories of consciousness, so enabling inferential synergy.

show abstract

HexagDLy—Processing hexagonally sampled data with CNNs in PyTorch

Cited by 42 publications

References 18 publications

Integrated World Modeling Theory (IWMT) Revisited

Integrated World Modeling Theory (IWMT) Revisited

Hexagonal Image Processing in the Context of Machine Learning: Conception of a Biologically Inspired Hexagonal Deep Learning Framework

An Integrated World Modeling Theory (IWMT) of consciousness: Combining Integrated Information and Global Neuronal Workspace Theories with the Free Energy Principle and Active Inference Framework; towards solving the Hard problem and characterizing agentic causation

Contact Info

Product

Resources

About