Artificial Representations Research Articles

Evolving Novel Gene Regulatory Networks for Structural Engineering Designs.

Engineering design optimization poses a significant challenge, usually requiring human expertise to discover superior solutions. Although various search techniques have been employed to generate diverse designs, their effectiveness is often limited by problem-specific parameter tuning, making them less generalizable and scalable. This article introduces a framework inspired by evolutionary and developmental (evo-devo) concepts, aiming to automate the evolution of structural engineering designs. In biological systems, evo-devo governs the growth of single-cell organisms into multicellular organisms through the use of gene regulatory networks (GRNs). GRNs are inherently complex and highly nonlinear, and this article explores the use of neural networks and genetic programming as artificial representations of GRNs to emulate such behaviors. To evolve a wide range of Pareto fronts for artificial GRNs, this article introduces a new technique, a real value-encoded neuroevolutionary method termed real-encoded NEAT (RNEAT). The performance of RNEAT is compared with that of two well-known evolutionary search techniques across different 2-D and 3-D problems. The experimental results demonstrate two key findings. First, the proposed framework effectively generates a population of GRNs that can produce diverse structures for both 2-D and 3-D problems. Second, the proposed RNEAT algorithm outperforms its competitors on more than 50% of the problems examined. These results validate the proof of concept underlying the proposed evo-devo-based engineering design evolution.

Elegans-AI: How the connectome of a living organism could model artificial neural networks

This paper introduces Elegans-AI models, a class of neural networks that leverage the connectome topology of the Caenorhabditis elegans to design deep and reservoir architectures. Utilizing deep learning models inspired by the connectome, this paper leverages the evolutionary selection process to consolidate the functional arrangement of biological neurons within their networks. The initial goal involves the conversion of natural connectomes into artificial representations. The second objective centers on embedding the complex circuitry topology of artificial connectomes into both deep learning and deep reservoir networks, highlighting their neural-dynamic short-term and long-term memory and learning capabilities. Lastly, our third objective aims to establish structural explainability by examining the heterophilic/homophilic properties within the connectome and their impact on learning capabilities. In our study, the Elegans-AI models demonstrate superior performance compared to similar models that utilize either randomly rewired artificial connectomes or simulated bio-plausible ones. Notably, these Elegans-AI models achieve a top-1 accuracy of 99.99% on both Cifar10 and Cifar100, and 99.84% on MNIST Unsup. They do this with significantly fewer learning parameters, particularly when reservoir configurations of the connectome are used. Our findings indicate a clear connection between bio-plausible network patterns, the small-world characteristic, and learning outcomes, emphasizing the significant role of evolutionary optimization in shaping the topology of artificial neural networks for improved learning performance.

Kiss/Crash

This paper describes the art installation of Kiss/Crash: a multi-screen work exploring the subject of AI-imagery and representation as well as the autobiographical themes of loneliness, desire, and intimacy in the digital age. The installation consists of three individual works in a shared space, Kiss/Crash, Me Kissing Me, and Crash Me, Gently, which all play with augmenting, inverting, and negating the iconic image of the kiss using diffusion-based image translation. In the production of this work, several potentially novel video translation techniques were developed and refined to create high-quality results central to these pieces. Throughout our research, we reflect on the nature of images and place diffusion models within a history of image-production technologies that artists have been contending with and responding to for the past one hundred years. This paper aims to extend that artistic tradition with a provocative, original aesthetic and technique that reveals the logic of AI imagery and hints at how our relationship to reality will continue to be stretched and shaped by artificial representations at an accelerating pace.

Analysis based on neural representation of natural object surfaces to elucidate the mechanisms of a trained AlexNet model.

Analysis and understanding of trained deep neural networks (DNNs) can deepen our understanding of the visual mechanisms involved in primate visual perception. However, due to the limited availability of neural activity data recorded from various cortical areas, the correspondence between the characteristics of artificial and biological neural responses for visually recognizing objects remains unclear at the layer level of DNNs. In the current study, we investigated the relationships between the artificial representations in each layer of a trained AlexNet model (based on a DNN) for object classification and the neural representations in various levels of visual cortices such as the primary visual (V1), intermediate visual (V4), and inferior temporal cortices. Furthermore, we analyzed the profiles of the artificial representations at a single channel level for each layer of the AlexNet model. We found that the artificial representations in the lower-level layers of the trained AlexNet model were strongly correlated with the neural representation in V1, whereas the responses of model neurons in layers at the intermediate and higher-intermediate levels of the trained object classification model exhibited characteristics similar to those of neural activity in V4 neurons. These results suggest that the trained AlexNet model may gradually establish artificial representations for object classification through the hierarchy of its network, in a similar manner to the neural mechanisms by which afferent transmission beginning in the low-level features gradually establishes object recognition as signals progress through the hierarchy of the ventral visual pathway.

INFLATION FORECASTS IN AMBON USING NEURAL NETWORK APPLICATIONS BACKPROPAGATION

An artificial Neural Network is the processing of information systems on certain characteristics which are artificial representations based on human neural networks. Artificial Neural Networks can be applied to various fields in human life, one of which is the economic field. In this study, the Artificial Neural Network is used to predict the inflation rate using the Backpropagation method. The data used in this study is 144 data, with 100 data as training data and 44 data as test data taken from the Central Statistics Agency of Maluku Province from 2008-2019. The best prediction accuracy level is obtained by using learning rate (a) = 0.1, Target Error = 0.000001, Maximum epoch = 500, network architecture 11-1, and 70% training data sharing scheme and 30% test data. The average absolute error percentage (MAPE) is 85.21%.

Jaringan Saraf Tiruan Memprediksi Nilai Pemelajaran Siswa Dengan Metode Backpropagation ( Studi kasus : SMP Negeri 1 Salapian)

Backpropagationcial neural networks are one of the artificial representations of the human brain that are always trying to stimulate the learning process of the human brain. Backpropagation is a gradient descent method to minimize the squared of the output error. Backprorpagation works through an iterative process using a set of sample data (training data), comparing the predicted value of the network with each sample data. In each process, the weight of the relation in the network is modified to minimize the Mean Squared Error value between the predicted value from the network and the actual value. The purpose of this thesis is to be able to help teachers at SMP Negeri 1 Salakaran to predict the value of student learning. In the calculation using the maximum epouch = 10000, the target error is 0.01, and the learning rate is 0.3, then there is a calculation result where the need ratio A has a value of 0.7517, which means that the value has decreased and D has a value of 0.9202 which means that this value has increased..

It’s Big Mouth!

The intermedial performance displayed in this video essay, highlights the need to re envisage Laura Mulvey’s 1975 theory of the male gaze in relation to the female-identifying ageing woman. The masculinised gaze that Mulvey discusses discards the ageing woman and relentlessly fetishizes the youthful state of femininity. I propose that Mulvey’s theory should be revised, along with a focus on rejecting and providing alternatives to the decline narrative that dominates ongoing contemporary perceptions of ageing (Gullette 1997; Mangan 2013). Applying this knowledge, along with methods of practice-based research, I argue that feminist performance art can fruitfully glorify the productive potentials of ageing femininities. This investigation illustrates how I combine digitised media with live performance to interrogate the positioning of the figure of the ageing Hollywood diva. My performative celebration of the diva is rooted in heightened performativity and the grotesque as a means of bursting through the confines of the male gaze, building on the work of performance artists such as Cindy Sherman and Lauren Barri Holstein. Highlighting my creative focus on the face as a medium for subversion, this work displays an engagement with a variety of textures and skins that the diva sheds and outgrows, alluding to the adaptability of the ageing woman. This video essay concludes by exploring the notion of the uncanny cyborgian diva. Using digital software to create an aged cyborgian version of myself, I continue to emphasise the resilient versatility of the diva. Throughout this work I ask; who is the cyborg diva? And what can we learn from her when considering the human problem of ageism? As I am 27 years old, my digital and artificial representations of ageing serve to expose the mechanisms behind my performance of age, highlight the constructedness of my performance techniques, and so challenge the problematically constructed concepts and perceptions of the ageing woman. *This video essay will consist of footage from my live performance of It’s Big Mouth! along with the film work that I shot as an accompaniment to it. The piece will also includes a written transcript for readers, along with a link to the video file*.

Resilient Algorithm In Predicting Fertilizer Imports by Major Countries

In the last five years (2013-2017) Indonesia’s fertilizer production experienced volatile growth, but overall tended to increase at a rate of 1.7% per year. The research aims to optimize artificial neural networks with a resilient backpropagation algorithm (Rprop), artificial neural networks are one of the artificial representations of the human brain that always tries to simulate the learning process in the human brain. Sample data used for optimization is fertilizer import data according to the main country of origin and uses 4 architectures, the best results are obtained between architectures 6-8-1, 6-12-1, 6-16-1, and 6-32-1 is architecture 6-32-1 with 100% accuracy.

Backpropagation Network Optimization Using One Step Secant (OSS) Algorithm

Education is one of the main indicators in national development efforts. The government in its efforts to realize national goals to educate the nation’s life has made a policy for compulsory 9-year schools, namely elementary and junior high schools. To find out how many residents use the education facilities provided by the government can be seen through school enrollment rates (SPR). A high School Participation Rate (SPR) means showing greater opportunities to access education in general. This study aims to optimize artificial neural networks with the One Step Secant (OSS) algorithm. Artificial Neural Network (ANN) is part of the artificial intelligence system (Artificial Intelligence, AI) which is one of the artificial representations of the human brain that always tries to simulate the learning process in the human brain. The sample data used for optimization is SPR Indonesia data by province. Using 4 architectural models with 5 input variables, 1 shadow layer and 1 output. The best results obtained between architectures 5-4-1, 5-8-1, 5-16-1 and 5-32-1 are architectures 5-16-1. Obtained prediction accuracy comparisons using the One Step Secant (OSS) algorithm and standard algorithms namely 96.97% and 100%. The standard algorithm is superior in accuracy, the One Step Secant (OSS) algorithm is superior in terms of iterations.

Jaringan Syaraf Tiruan untuk Memprediksi Penjualan Kelapa Sawit Menggunakan Algoritma Backpropagation

This study discusses the prediction of palm oil sales using artificial neural networks, which is one of the artificial representations of the human brain that always tries to simulate the learning process of the human brain. The application uses a backpropagation algorithm where the data entered is the number of sold. Then artificial neural networks are formed by determining the number of units per layer. After the networks is formed, training is carried out from the grouped data. Experiments are carried out with an architecture consisting of input units, hidden units, output units and architecture. Testing is done with matlab software. For now the competition for palm oil sales is getting tougher. Predictions with the best accuracy use the 12-2-1 architecture with an accuracy rate of 92% and the lowest level of accuracy using 12-6-1 architecture with an accuracy rate of 58%

Analisis Jaringan Syaraf Tiruan untuk Memprediksi Jumlah Narapidana pada Lembaga Pemasyarakatan Simalungun dengan Metode Backpropagation

The author has conducted research at the Simalungun District Prosecutor's Office and found the problem of prison rooms that did not match the number of prisoners which caused a lack of security and a lack of detention facilities and risked inmates to flee. Artificial Neural Network which is one of the artificial representations of the human brain that always tries to simulate the learning process of the human brain. The application uses the Backpropagation algorithm where the data entered is the number of prisoners. Then Artificial Neural Networks are formed by determining the number of units per layer. Once formed, training is carried out from the data that has been grouped. Experiments are carried out with a network architecture consisting of input units, hidden units, and output units. Testing using Matlab software. For now, the number of prisoners continues to increase. Predictions with the best accuracy use the 12-3-1 architecture with an accuracy rate of 75% and the lowest level of accuracy using 12-4-1 architecture with an accuracy rate of 25%.

‘Africans’ and the ‘Chinese’ Exhibited in Finland in the years 1926–1928

Abstract This article analyses two peculiar cases of ‘otherness’ (alterity), as witnessed on stage at an exhibition of Chinese and African cultures presented by the Finnish Missionary Society from 1926-1928. This exhibition consisted of a man-made figure (re)presenting the Ovambo (African) culture of South-West Africa, in concert with Chinese figures who were made to represent the contemporary culture of China. Of note is the fact that the Chinese part of the exhibition was not as contemporary as proposed. In fact, it had imperial qualities. Both sections of the exhibition were ‘made-in-Finland’ type artificial representations which bordered on total inauthenticity as the organizers did not have anything more indigenous or native to the lands presented at hand. In short, they had to be both inventive and resourceful. In any case, the public (urban middle- and high-class, schoolchildren, teachers, academic and educated people in general) did not seem to care about the ambiguous mixture of apparent (‘white’) identity and (‘black’, Chinese) alterities as they were – for the most part – satisfied with the exhibition, which served as a very rare attraction in Finland at that time.

New Method for Locker Door with Face Security System Using Backpropagation Algorithm

Lockers are one of the facilities that people use to store stuff. Artificial neural networks are computational systems where architecture and operations are inspired by the knowledge of biological neurons in the brain, which is one of the artificial representations of the human brain that always tries to stimulate the learning process of the human brain. One of the utilization of artificial neural network is for pattern recognition. The face of a person must be different but sometimes has a shape similar to the face of others, because the facial pattern is a good pattern to try to be recognized by using artificial neural networks. Pattern recognition on artificial neural network can be done by back propagation method. Back propagation method consists of input layer, hidden layer and output layer.

Prevention 0f Unwanted Free-Declaration of Static Obstacles in Probability Occupancy Grids

Obstacle detection and avoidance are major research fields in unmanned aviation. Map based obstacle detection approaches often use discrete world representations such as probabilistic grid maps to fuse incremental environment data from different views or sensors to build a comprehensive representation. The integration of continuous measurements into a discrete representation can result in rounding errors which, in turn, leads to differences between the artificial model and real environment. The cause of these deviations is a low spatial resolution of the world representation comparison to the used sensor data. Differences between artificial representations which are used for path planning or obstacle avoidance and the real world can lead to unexpected behavior up to collisions with unmapped obstacles. This paper presents three approaches to the treatment of errors that can occur during the integration of continuous laser measurement in the discrete probabilistic grid. Further, the quality of the error prevention and the processing performance are compared with real sensor data.

Bodily Intra-actions with Biometric Devices

We investigated the interface between biomedia and humans by inviting participants to interact with biometric devices that measured and visualized their body data. At first, they struggled with the alienating and disembodying nature of the devices and the constrained, reductionist representation of data. Through their bodily interactions with these devices, however, participants reframed the data and inserted their bodies into the process of data collection. Drawing on the ideas of Bergson, Grosz, Merleau-Ponty and Bachelard, we argue that by working with their subjectivity in a mediated process of becoming, participants ‘filled in the intervals’ of the visual representations of their bodies to interpret them in ways that marked the duration and meaning of their selves. We conclude that even when presented with artificial representations, individuals convert the representation of the data into narratives inspired by their embodied experience, and the ‘virtual’ pasts of their own lives.

A review of plant‐flow interactions on salt marshes: the importance of vegetation structure and plant mechanical characteristics

Observations of plant‐flow interactions on salt marshes have revealed a highly complex process dominated by the tightly coupled effects of plant characteristics and hydrodynamic conditions. This paper highlights the importance of vegetation structures such as plant density and height, as well as their spatial variability and mechanical properties including flexibility, upon energy dissipation and flow modification. Many field, laboratory and modeling studies which attempt to predict flow dissipation or improve our understanding of plant‐flow interactions use simplified structural measures of salt marsh vegetation or artificial representations. These simplifications neglect important plant and canopy elements and are unlikely to be truly representative of their natural counterparts. Such approaches limit our understanding of plant‐flow interactions and potentially compromise the predictive accuracy and application of numerical flow models. It is important therefore that improved techniques to measure vegetation structure are adopted in order to better define the key relationships between measurable plant characteristics and drag‐relevant plant properties. WIREs Water 2015, 2:669–681. doi: 10.1002/wat2.1103This article is categorized under: Water and Life > Stresses and Pressures on Ecosystems

Consequences of Landscape Fragmentation on Lyme Disease Risk: A Cellular Automata Approach

The abundance of infected Ixodid ticks is an important component of human risk of Lyme disease, and various empirical studies have shown that this is associated, at least in part, to landscape fragmentation. In this study, we aimed at exploring how varying woodland fragmentation patterns affect the risk of Lyme disease, through infected tick abundance. A cellular automata model was developed, incorporating a heterogeneous landscape with three interactive components: an age-structured tick population, a classical disease transmission function, and hosts. A set of simplifying assumptions were adopted with respect to the study objective and field data limitations. In the model, the landscape influences both tick survival and host movement. The validation of the model was performed with an empirical study. Scenarios of various landscape configurations (focusing on woodland fragmentation) were simulated and compared. Lyme disease risk indices (density and infection prevalence of nymphs) differed considerably between scenarios: (i) the risk could be higher in highly fragmented woodlands, which is supported by a number of recently published empirical studies, and (ii) grassland could reduce the risk in adjacent woodland, which suggests landscape fragmentation studies of zoonotic diseases should not focus on the patch-level woodland patterns only, but also on landscape-level adjacent land cover patterns. Further analysis of the simulation results indicated strong correlations between Lyme disease risk indices and the density, shape and aggregation level of woodland patches. These findings highlight the strong effect of the spatial patterns of local host population and movement on the spatial dynamics of Lyme disease risks, which can be shaped by woodland fragmentation. In conclusion, using a cellular automata approach is beneficial for modelling complex zoonotic transmission systems as it can be combined with either real world landscapes for exploring direct spatial effects or artificial representations for outlining possible empirical investigations.

Realism and Realistic Representation in the Digital Age

TODAY, WHEN REALISM IN FILM COMMINGLES so frequently with digital technology and is often diluted by the extended use of editing, there is a certain urgency to revisit its established formal practices. ample potential for image control and manipulation provided by digital technology has stirred a great Interest in postproduction, particularly in the areas of digital compositing and digital editing. For one thing, the easy handling in making a cut and the maneuverability in handling rather complicated editing options have fostered that interest (Murch 107-18). Another contributing factor is that editing is no longera horizontal manipulative sequential process but is vertical too. inclusion of digital special-effects software (e.g., the Inferno compositing tool) allows the editor to manipulate backgrounds and other small visual details in the frame simultaneously (130). A good example is David Fincher's film Zodiac (2007). Looking for and authenticity, Fincher ends with outstanding digital effects, recreating with historical accuracy parts of San Francisco in 1969 and 1970 when the real events, the Zodiac murders, took place (Robertson). present fascination with visual manipulation not only has brought Into question but also has brought into focus a breed of film whose creative sensibility is manifested in the way he or she perceives reality. Namely, reality is seen not as something to be captured in the purest way possible by the camera lens but rather as something to be constructed. As Phillip Rosen points out, this has essentially splintered from the old established production practice that Involves dependence on some minimum of the presence of the real objects they represent Change Mummified 301). The fact that a digital image is composed through the manipulation of numbers and not physical substances (306) means that this director, if he or she chooses, is no longer bound to the existential connection between a specific and the signifier, [where] the latter will always provide the subject with irrefutable testimony as to the real existence of the referent (Rosen, History of I mage 13). Stephen Prince sees this radical shift from the old production practice as surmountable if we overlook the image's indexical requirement and adopt a correspondencebased model of cinematic representation (399). That is, in spite of the image's lack of referential root, and in spite of the indexical (the photographic) and the non-indexical (the digital- CGI) often commingling, either embedded within the frame or coexisting side by side within a sequence, the viewer is able to connect and accept the image as if it were a photographic image of the portrayed realism. film image, whether it has an indexical or not, does not detract from the viewer's acceptance of its realism. In other words, for Prince the viewer's interest is no longer in how the film expresses its realism, whether it is highly stylized through the usage of technology or not, but about the kinds of linkages that connect the represented fictionalized reality of a given film to the visual and social coordinates of our own three-dimensional world [visual credibility]. Such focus need not reinstate Indexicality as the ground of realism (400). Aesthetically speaking, this commingling of the digital with the photographic image poses some interesting questions: (1) if both the digital and the photographic image are artificial representations of reality, which of the two is more vertically true to reality? Or are both at the same level? If not, what are the differences? (2) In what ways does this technological new director differ from those Andre Bazin recognized as having put their faith in reality rather than in the image? (Evolution 24). (3) Is this new director truly concerned with reality? These are some of the questions this article wrestles with in order to grasp some of the aesthetic changes brought by the digital technology in today's film realism. …

Computational evolution: taking liberties

Evolution has, for a long time, inspired computer scientists to produce computer models mimicking its behavior. Evolutionary algorithm (EA) is one of the areas where this approach has flourished. EAs have been used to model and study evolution, but they have been especially developed for their aptitude as optimization tools for engineering. Developed models are quite simple in comparison with their natural sources of inspiration. However, since EAs run on computers, we have the freedom, especially in optimization models, to test approaches both realistic and outright speculative, from the biological point of view. In this article, we discuss different common evolutionary algorithm models, and then present some alternatives of interest. These include biologically inspired models, such as co-evolution and, in particular, symbiogenetics and outright artificial operators and representations. In each case, the advantages of the modifications to the standard model are identified. The other area of computational evolution, which has allowed us to study basic principles of evolution and ecology dynamics, is the development of artificial life platforms for open-ended evolution of artificial organisms. With these platforms, biologists can test theories by directly manipulating individuals and operators, observing the resulting effects in a realistic way. An overview of the most prominent of such environments is also presented. If instead of artificial platforms we use the real world for evolving artificial life, then we are dealing with evolutionary robotics (ERs). A brief description of this area is presented, analyzing its relations to biology. Finally, we present the conclusions and identify future research avenues in the frontier of computation and biology. Hopefully, this will help to draw the attention of more biologists and computer scientists to the benefits of such interdisciplinary research.

Alternatyvus pilietinis ugdymas ir socialinė propaganda

Straipsnyje nagrinėjama šiuolaikinės demokratinės visuomenės raida ir jos sąmoningumas, atsižvelgiant į santykį su spektaklio visuomene, su šiuolaikinėmis įtikinėjimo formomis ir pilietinio lavinimo problemomis. Šiuolaikinės visuomenės demokratinė savivalda sunkiai galima be viešųjų ryšių technologijų, socialinės propagandos. Jų aktualumą lemia heterogeninės, skirtingų kompetencijų, interesų ir aktyvumo socialinės grupės. Straipsnyje nagrinėjama socialinė inžinerija, socialinė propaganda, socialinė reklama ir pamatuota demokratinė visuomenės raida. Iš dalies kritikuojama K. Popperio utopinės ir dalinės socialinės inžinerijos perskyra nurodant, kad falibilizmo principas nėra tiesiogiai perkeliamas iš gamtos mokslų į socialinius. Šiuolaikinė visuomenė privalo plėtoti projektinį mąstymą ir projektų konkurenciją, o jų alternatyvumas užtikrina utopinio mąstymo žalos mažinimą ir išsaugo kūrybingumą. Taigi falibilizmas yra pakeičiamas alternatyvų raida. Atitinkamai yra nagrinėjamas žiniasklaidos vaidmuo remiant socialinę propagandą, atsižvelgiant į skirtingus jos dalyvavimo, įtrauktumo lygius. Straipsnis skiria: (a) vienpusę socialinę propagandą, kuri formuoja vienmatį žmogų, propagandos subjektą, skatina pakeistinį mąstymą, ir (b) alternatyvią socialinę, kultūrinę propagandą kaip demokratinį visuomenės savivaldos principą. Teigiama, kad alternatyvumas yra tiesiogiai susietas su viešosiomis erdvėmis. Viešuma užtikrina dialogizmą, kuriame esmingai gyvena ir savo rūpesčius apmąsto žmogus. Dialogizmo ir viešųjų erdvių, kur tas dialogas įmanomas, griovimas kartu reiškia ir demokratijos eroziją bei autoritarizmo ir vienpusės manipuliacijos didėjimą. Norint šių reiškinių išvengti, būtina skatinti alternatyvų pilietinį ugdymą, kurio tikslas – mokytis protesto, manifestacijų, alternatyvių reprezentacijų ir mikroakcijų formų. Pažymimos sąsajos tarp socialinės propagandos ir plakatų, šūkių, agitacinių straipsnių ir feljetonų žanrų. Svarbu kaupti ir analizuoti alternatyvių sąjūdžių patirtį ir kelti protesto kultūrą, kurios viena išraiškų yra alternatyvių socialinių ir kultūrinių projektų teikimas ir kompetencijų šioje sferoje didinimas, mažinant monopolistines ir valstybės centristines tendencijas, didinant bendruomenių savivaldą.