It is already well known that environmental variation has a big effect on real evolution, and similar effects have been found in evolutionary artificial life simulations. In particular, a lot of research has been carried out on how the various evolutionary outcomes depend on the noise distributions representing the environmental changes, and how important it is for models to use inverse power-law distributions with the right noise colour. However, there are two distinct factors of relevance—the average total magnitude of change per unit time and the distribution of individual change magnitudes—and misleading results may emerge if those factors are not properly separated. This article makes use of an existing agent-based artificial life modeling framework to explore this issue using models previously tried and tested for other purposes. It begins by demonstrating how the total magnitude and distribution effects can easily be confused, and goes on to show how it is possible to untangle the influence of these interacting factors by using correlation-based normalization. It then presents a series of simulation results demonstrating that interesting dependencies on the noise distribution remain after separating those factors, but many effects involving the noise colour of inverse power-law distributions disappear, and very similar results arise across restricted-range white-noise distributions. The average total magnitude of change per unit time is found to have a substantial effect on the simulation outcomes, but the distribution of individual changes has very little effect. A robust counterexample is thereby provided to the idea that it is always important to use accurate environmental change distributions in artificial life models.
{"title":"Effect of Environmental Change Distribution on Artificial Life Simulations","authors":"John A. Bullinaria","doi":"10.1162/artl_a_00366","DOIUrl":"10.1162/artl_a_00366","url":null,"abstract":"It is already well known that environmental variation has a big effect on real evolution, and similar effects have been found in evolutionary artificial life simulations. In particular, a lot of research has been carried out on how the various evolutionary outcomes depend on the noise distributions representing the environmental changes, and how important it is for models to use inverse power-law distributions with the right noise colour. However, there are two distinct factors of relevance—the average total magnitude of change per unit time and the distribution of individual change magnitudes—and misleading results may emerge if those factors are not properly separated. This article makes use of an existing agent-based artificial life modeling framework to explore this issue using models previously tried and tested for other purposes. It begins by demonstrating how the total magnitude and distribution effects can easily be confused, and goes on to show how it is possible to untangle the influence of these interacting factors by using correlation-based normalization. It then presents a series of simulation results demonstrating that interesting dependencies on the noise distribution remain after separating those factors, but many effects involving the noise colour of inverse power-law distributions disappear, and very similar results arise across restricted-range white-noise distributions. The average total magnitude of change per unit time is found to have a substantial effect on the simulation outcomes, but the distribution of individual changes has very little effect. A robust counterexample is thereby provided to the idea that it is always important to use accurate environmental change distributions in artificial life models.","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":null,"pages":null},"PeriodicalIF":2.6,"publicationDate":"2022-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48786041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The emergence of sex robots raises important issues about what it means to be human and the commodification of love, companionship, and sex. This commentary discusses the following question: If some members of society relate to robots as “humans,” what does this mean for society’s conceptualisation of personhood and intimate relationships? How love is expressed between individuals is normally considered a very private expression of companionship that should remain in the private sphere. This article examines whether sex robots should be subject to public regulation given the broader societal impacts of their ability to emotionally connect and elicit empathy from humans.
{"title":"A Response to Paolo Euron’s “Uncanny Beauty: Aesthetics of Companionship, Love, and Sex Robots”","authors":"Maria O’Sullivan","doi":"10.1162/artl_a_00363","DOIUrl":"10.1162/artl_a_00363","url":null,"abstract":"The emergence of sex robots raises important issues about what it means to be human and the commodification of love, companionship, and sex. This commentary discusses the following question: If some members of society relate to robots as “humans,” what does this mean for society’s conceptualisation of personhood and intimate relationships? How love is expressed between individuals is normally considered a very private expression of companionship that should remain in the private sphere. This article examines whether sex robots should be subject to public regulation given the broader societal impacts of their ability to emotionally connect and elicit empathy from humans.","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":null,"pages":null},"PeriodicalIF":2.6,"publicationDate":"2022-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47305172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Can machines ever be sentient? Could they perceive and feel things; be conscious of their surroundings? What are the prospects of achieving sentience in a machine? What are the dangers associated with such an endeavor, and is it even ethical to embark on such a path to begin with? In the series of articles of this column, I discuss one possible path towards “General Intelligence” in machines: to use the process of Darwinian evolution to produce artificial brains that can be grafted onto mobile robotic platforms, with the goal of achieving fully embodied sentient machines.
{"title":"Making Artificial Brains: Components, Topology, and Optimization","authors":"Christoph Adami","doi":"10.1162/artl_a_00364","DOIUrl":"10.1162/artl_a_00364","url":null,"abstract":"Can machines ever be sentient? Could they perceive and feel things; be conscious of their surroundings? What are the prospects of achieving sentience in a machine? What are the dangers associated with such an endeavor, and is it even ethical to embark on such a path to begin with? In the series of articles of this column, I discuss one possible path towards “General Intelligence” in machines: to use the process of Darwinian evolution to produce artificial brains that can be grafted onto mobile robotic platforms, with the goal of achieving fully embodied sentient machines.","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":null,"pages":null},"PeriodicalIF":2.6,"publicationDate":"2022-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46283792","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We demonstrate a novel computational architecture based on fluid convection logic gates and heat flux-mediated information flows. Our previous work demonstrated that Boolean logic operations can be performed by thermally driven convection flows. In this work, we use numerical simulations to demonstrate a different , but universal Boolean logic operation (NOR), performed by simpler convective gates. The gates in the present work do not rely on obstacle flows or periodic boundary conditions, a significant improvement in terms of experimental realizability. Conductive heat transfer links can be used to connect the convective gates, and we demonstrate this with the example of binary half addition. These simulated circuits could be constructed in an experimental setting with modern, 2-dimensional fluidics equipment, such as a thin layer of fluid between acrylic plates. The presented approach thus introduces a new realm of unconventional, thermal fluid-based computation.
{"title":"Computation by Convective Logic Gates and Thermal Communication","authors":"Stuart Bartlett;Andrew K. Gao;Yuk L. Yung","doi":"10.1162/artl_a_00358","DOIUrl":"10.1162/artl_a_00358","url":null,"abstract":"We demonstrate a novel computational architecture based on fluid convection logic gates and heat flux-mediated information flows. Our previous work demonstrated that Boolean logic operations can be performed by thermally driven convection flows. In this work, we use numerical simulations to demonstrate a different , but universal Boolean logic operation (NOR), performed by simpler convective gates. The gates in the present work do not rely on obstacle flows or periodic boundary conditions, a significant improvement in terms of experimental realizability. Conductive heat transfer links can be used to connect the convective gates, and we demonstrate this with the example of binary half addition. These simulated circuits could be constructed in an experimental setting with modern, 2-dimensional fluidics equipment, such as a thin layer of fluid between acrylic plates. The presented approach thus introduces a new realm of unconventional, thermal fluid-based computation.","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":null,"pages":null},"PeriodicalIF":2.6,"publicationDate":"2022-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45198390","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Julian’s work is well known throughout the Artificial Life community: His Cartesian genetic programming (CGP) and in materio computing are foundational concepts. He also made contributions in morphological computing and neurocomputing, all based on his fascination with evolution as a means of attacking and solving problems. Like many in the ALife community, he had an interdisciplinary career, commencing with a first degree in Physics and a PhD in Mathematics, followed by research in Natural Computing and material computing at the universities of Napier, Birmingham, and York in the UK. Julian invented CGP (Miller, 1999), a way of encoding graph programs (functional nodes connected by edges) in a string of integers, allowing the string to be evolved in the standard way, with the graph (located on a Cartesian grid, hence its name) produced as the result of a genotype to phenotype mapping. From this simple beginning, Julian and his students continued to develop the approach, and other researchers joined in. Ten years later, the field had grown significantly, with many researchers both using CGP in their own work and extending the original concept. Indeed, the field had grown enough that Julian could edit an entire book on the topic (Miller, 2011).
{"title":"Julian Francis Miller, 1955–2022","authors":"Susan Stepney;Alan Dorin","doi":"10.1162/artl_a_00371","DOIUrl":"10.1162/artl_a_00371","url":null,"abstract":"Julian’s work is well known throughout the Artificial Life community: His Cartesian genetic programming (CGP) and in materio computing are foundational concepts. He also made contributions in morphological computing and neurocomputing, all based on his fascination with evolution as a means of attacking and solving problems. Like many in the ALife community, he had an interdisciplinary career, commencing with a first degree in Physics and a PhD in Mathematics, followed by research in Natural Computing and material computing at the universities of Napier, Birmingham, and York in the UK. Julian invented CGP (Miller, 1999), a way of encoding graph programs (functional nodes connected by edges) in a string of integers, allowing the string to be evolved in the standard way, with the graph (located on a Cartesian grid, hence its name) produced as the result of a genotype to phenotype mapping. From this simple beginning, Julian and his students continued to develop the approach, and other researchers joined in. Ten years later, the field had grown significantly, with many researchers both using CGP in their own work and extending the original concept. Indeed, the field had grown enough that Julian could edit an entire book on the topic (Miller, 2011).","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":null,"pages":null},"PeriodicalIF":2.6,"publicationDate":"2022-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47127970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the last few years there has been a lively debate on humanoid robots interacting with humans in fields where human appearance and likeness may be essential. The debate has been bolstered by advancing AI technologies as well as increasing economic interest and public attention. The feasibility, inevitability, or ethical opportunity of companionship, love, and sex robots has been discussed. I propose a philosophical and cultural approach, applying the strategies of aesthetics and literary theory to the field of artificial beings, in order to understand reasons, use, limits, and possibilities expressed by the technology applied to companionship, love, and sex robots in the contemporary cultural and social context. In dealing with aesthetics, I will state how cognitive, biological, and ethical aspects are involved, how beauty is relatable to a robot’s physical appearance, and how the aesthetics of artificial beings may offer new existential experiences.
{"title":"Uncanny Beauty: Aesthetics of Companionship, Love, and Sex Robots","authors":"Paolo Euron","doi":"10.1162/artl_a_00361","DOIUrl":"10.1162/artl_a_00361","url":null,"abstract":"In the last few years there has been a lively debate on humanoid robots interacting with humans in fields where human appearance and likeness may be essential. The debate has been bolstered by advancing AI technologies as well as increasing economic interest and public attention. The feasibility, inevitability, or ethical opportunity of companionship, love, and sex robots has been discussed. I propose a philosophical and cultural approach, applying the strategies of aesthetics and literary theory to the field of artificial beings, in order to understand reasons, use, limits, and possibilities expressed by the technology applied to companionship, love, and sex robots in the contemporary cultural and social context. In dealing with aesthetics, I will state how cognitive, biological, and ethical aspects are involved, how beauty is relatable to a robot’s physical appearance, and how the aesthetics of artificial beings may offer new existential experiences.","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":null,"pages":null},"PeriodicalIF":2.6,"publicationDate":"2022-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42641639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-24DOI: 10.48550/arXiv.2203.13050
James M. Borg, Andrew Buskell, Rohan Kapitány, S. Powers, E. Reindl, C. Tennie
The goal of Artificial Life research, as articulated by Chris Langton, is "to contribute to theoretical biology by locating life-as-we-know-it within the larger picture of life-as-it-could-be." The study and pursuit of open-ended evolution in artificial evolutionary systems exemplify this goal. However, open-ended evolution research is hampered by two fundamental issues: the struggle to replicate open-endedness in an artificial evolutionary system and our assumption that we only have one system (genetic evolution) from which to draw inspiration. We argue not only that cultural evolution should be seen as another real-world example of an open-ended evolutionary system but that the unique qualities seen in cultural evolution provide us with a new perspective from which we can assess the fundamental properties of, and ask new questions about, open-ended evolutionary systems, especially with regard to evolved open-endedness and transitions from bounded to unbounded evolution. Here we provide an overview of culture as an evolutionary system, highlight the interesting case of human cultural evolution as an open-ended evolutionary system, and contextualize cultural evolution by developing a new framework of (evolved) open-ended evolution. We go on to provide a set of new questions that can be asked once we consider cultural evolution within the framework of open-ended evolution and introduce new insights that we may be able to gain about evolved open-endedness as a result of asking these questions.
{"title":"Evolved Open-Endedness in Cultural Evolution: A New Dimension in Open-Ended Evolution Research","authors":"James M. Borg, Andrew Buskell, Rohan Kapitány, S. Powers, E. Reindl, C. Tennie","doi":"10.48550/arXiv.2203.13050","DOIUrl":"https://doi.org/10.48550/arXiv.2203.13050","url":null,"abstract":"The goal of Artificial Life research, as articulated by Chris Langton, is \"to contribute to theoretical biology by locating life-as-we-know-it within the larger picture of life-as-it-could-be.\" The study and pursuit of open-ended evolution in artificial evolutionary systems exemplify this goal. However, open-ended evolution research is hampered by two fundamental issues: the struggle to replicate open-endedness in an artificial evolutionary system and our assumption that we only have one system (genetic evolution) from which to draw inspiration. We argue not only that cultural evolution should be seen as another real-world example of an open-ended evolutionary system but that the unique qualities seen in cultural evolution provide us with a new perspective from which we can assess the fundamental properties of, and ask new questions about, open-ended evolutionary systems, especially with regard to evolved open-endedness and transitions from bounded to unbounded evolution. Here we provide an overview of culture as an evolutionary system, highlight the interesting case of human cultural evolution as an open-ended evolutionary system, and contextualize cultural evolution by developing a new framework of (evolved) open-ended evolution. We go on to provide a set of new questions that can be asked once we consider cultural evolution within the framework of open-ended evolution and introduce new insights that we may be able to gain about evolved open-endedness as a result of asking these questions.","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":null,"pages":null},"PeriodicalIF":2.6,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48598564","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Understanding how evolutionary agents behave in complex environments is a challenging problem. Agents can be faced with complex fitness landscapes derived from multi-stage tasks, interaction with others, and limited environmental feedback. Agents that evolve to overcome these can sometimes access greater fitness, as a result of factors such as cooperation and tool use. However, it is often difficult to explain why evolutionary agents behave in certain ways, and what specific elements of the environment or task may influence the ability of evolution to find goal-achieving behaviours; even seemingly simple environments or tasks may contain features that affect agent evolution in unexpected ways. We explore principled simplification of evolutionary agent-based models, as a possible route to aiding their explainability. Using the River Crossing Task (RCT) as a case study, we draw on analysis in the Minimal River Crossing (RC-) Task testbed, which was designed to simplify the original task while keeping its key features. Using this method, we present new analysis concerning when agents evolve to successfully complete the RCT. We demonstrate that the RC- environment can be used to understand the effect that a cost to movement has on agent evolution, and that these findings can be generalised back to the original RCT. Then, we present new insight into the use of principled simplification in understanding evolutionary agents. We find evidence that behaviour dependent on features that survive simplification, such as problem structure, are amenable to prediction; while predicting behaviour dependent on features that are typically reduced in simplification, such as scale, can be invalid.
{"title":"Explaining Evolutionary Agent-Based Models via Principled Simplification","authors":"Chloe M. Barnes;Abida Ghouri;Peter R. Lewis","doi":"10.1162/artl_a_00339","DOIUrl":"10.1162/artl_a_00339","url":null,"abstract":"Understanding how evolutionary agents behave in complex environments is a challenging problem. Agents can be faced with complex fitness landscapes derived from multi-stage tasks, interaction with others, and limited environmental feedback. Agents that evolve to overcome these can sometimes access greater fitness, as a result of factors such as cooperation and tool use. However, it is often difficult to explain why evolutionary agents behave in certain ways, and what specific elements of the environment or task may influence the ability of evolution to find goal-achieving behaviours; even seemingly simple environments or tasks may contain features that affect agent evolution in unexpected ways. We explore principled simplification of evolutionary agent-based models, as a possible route to aiding their explainability. Using the River Crossing Task (RCT) as a case study, we draw on analysis in the Minimal River Crossing (RC-) Task testbed, which was designed to simplify the original task while keeping its key features. Using this method, we present new analysis concerning when agents evolve to successfully complete the RCT. We demonstrate that the RC- environment can be used to understand the effect that a cost to movement has on agent evolution, and that these findings can be generalised back to the original RCT. Then, we present new insight into the use of principled simplification in understanding evolutionary agents. We find evidence that behaviour dependent on features that survive simplification, such as problem structure, are amenable to prediction; while predicting behaviour dependent on features that are typically reduced in simplification, such as scale, can be invalid.","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":null,"pages":null},"PeriodicalIF":2.6,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39377394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In genetic programming, an evolutionary method for producing computer programs that solve specified computational problems, parent selection is ordinarily based on aggregate measures of performance across an entire training set. Lexicase selection, by contrast, selects on the basis of performance on random sequences of training cases; this has been shown to enhance problem-solving power in many circumstances. Lexicase selection can also be seen as better reflecting biological evolution, by modeling sequences of challenges that organisms face over their lifetimes. Recent work has demonstrated that the advantages of lexicase selection can be amplified by down-sampling, meaning that only a random subsample of the training cases is used each generation. This can be seen as modeling the fact that individual organisms encounter only subsets of the possible environments and that environments change over time. Here we provide the most extensive benchmarking of down-sampled lexicase selection to date, showing that its benefits hold up to increased scrutiny. The reasons that down-sampling helps, however, are not yet fully understood. Hypotheses include that down-sampling allows for more generations to be processed with the same budget of program evaluations; that the variation of training data across generations acts as a changing environment, encouraging adaptation; or that it reduces overfitting, leading to more general solutions. We systematically evaluate these hypotheses, finding evidence against all three, and instead draw the conclusion that down-sampled lexicase selection's main benefit stems from the fact that it allows the evolutionary process to examine more individuals within the same computational budget, even though each individual is examined less completely.
{"title":"Problem-Solving Benefits of Down-Sampled Lexicase Selection","authors":"Thomas Helmuth;Lee Spector","doi":"10.1162/artl_a_00341","DOIUrl":"10.1162/artl_a_00341","url":null,"abstract":"In genetic programming, an evolutionary method for producing computer programs that solve specified computational problems, parent selection is ordinarily based on aggregate measures of performance across an entire training set. Lexicase selection, by contrast, selects on the basis of performance on random sequences of training cases; this has been shown to enhance problem-solving power in many circumstances. Lexicase selection can also be seen as better reflecting biological evolution, by modeling sequences of challenges that organisms face over their lifetimes. Recent work has demonstrated that the advantages of lexicase selection can be amplified by down-sampling, meaning that only a random subsample of the training cases is used each generation. This can be seen as modeling the fact that individual organisms encounter only subsets of the possible environments and that environments change over time. Here we provide the most extensive benchmarking of down-sampled lexicase selection to date, showing that its benefits hold up to increased scrutiny. The reasons that down-sampling helps, however, are not yet fully understood. Hypotheses include that down-sampling allows for more generations to be processed with the same budget of program evaluations; that the variation of training data across generations acts as a changing environment, encouraging adaptation; or that it reduces overfitting, leading to more general solutions. We systematically evaluate these hypotheses, finding evidence against all three, and instead draw the conclusion that down-sampled lexicase selection's main benefit stems from the fact that it allows the evolutionary process to examine more individuals within the same computational budget, even though each individual is examined less completely.","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":null,"pages":null},"PeriodicalIF":2.6,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39377911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Artificial neural networks (ANNs) were originally inspired by the brain; however, very few models use evolution and development, both of which are fundamental to the construction of the brain. We describe a simple neural model, called IMPROBED, in which two neural programs construct an artificial brain that can simultaneously solve multiple computational problems. One program represents the neuron soma and the other the dendrite. The soma program decides whether neurons move, change, die, or replicate. The dendrite program decides whether dendrites extend, change, die, or replicate. Since developmental programs build networks that change over time, it is necessary to define new problem classes that are suitable to evaluate such approaches. We show that the pair of evolved programs can build a single network from which multiple conventional ANNs can be extracted, each of which can solve a different computational problem. Our approach is quite general and it could be applied to a much wider variety of problems.
{"title":"IMPROBED: Multiple Problem-Solving Brain via Evolved Developmental Programs","authors":"Julian Francis Miller","doi":"10.1162/artl_a_00346","DOIUrl":"10.1162/artl_a_00346","url":null,"abstract":"Artificial neural networks (ANNs) were originally inspired by the brain; however, very few models use evolution and development, both of which are fundamental to the construction of the brain. We describe a simple neural model, called IMPROBED, in which two neural programs construct an artificial brain that can simultaneously solve multiple computational problems. One program represents the neuron soma and the other the dendrite. The soma program decides whether neurons move, change, die, or replicate. The dendrite program decides whether dendrites extend, change, die, or replicate. Since developmental programs build networks that change over time, it is necessary to define new problem classes that are suitable to evaluate such approaches. We show that the pair of evolved programs can build a single network from which multiple conventional ANNs can be extracted, each of which can solve a different computational problem. Our approach is quite general and it could be applied to a much wider variety of problems.","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":null,"pages":null},"PeriodicalIF":2.6,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39600012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}