In this paper an Artificial Neural Network (ANN) model was used to help cars dealers recognize the many characteristics of cars, including manufacturers, their location and classification of cars according to several categories including: Make, Model, Type, Origin, DriveTrain, MSRP, Invoice, EngineSize, Cylinders, Horsepower, MPG_Highway, Weight, Wheelbase, Length. ANN was used in prediction of the number of miles per gallon when the car is driven in the city(MPG_City). The results showed that ANN model was able to predict MPG_City with (...) 97.50 % accuracy. The factor of DriveTrain has the most influence on MPG_City evaluation. Similar studies can be carried out for the evaluation of other characteristics of cars. (shrink)

Recent breakthroughs in artificial intelligence have primarily resulted from training deep neural networks (DNNs) with vast numbers of adjustable parameters on enormous datasets. Due to their complex internal structure, DNNs are frequently characterized as inscrutable ``black boxes,'' making it challenging to interpret the mechanisms underlying their impressive performance. This opacity creates difficulties for explanation, safety assurance, trustworthiness, and comparisons to human cognition, leading to divergent perspectives on these systems. This chapter examines recent developments in interpretability methods for DNNs, (...) with a focus on interventionist approaches inspired by causal explanation in philosophy of science. We argue that these methods offer a promising avenue for understanding how DNNs process information compared to merely behavioral benchmarking and correlational probing. We review key interventionist methods and illustrate their application through practical case studies. These methods allow researchers to identify and manipulate specific computational components within DNNs, providing insights into their causal structure and internal representations. We situate these approaches within the broader framework of causal abstraction, which aims to align low-level neural computations with high-level interpretable models. While acknowledging current limitations, we contend that interventionist methods offer a path towards more rigorous and theoretically grounded interpretability research, potentially informing both AI development and computational cognitive neuroscience. (shrink)

In artificial intelligence, recent research has demonstrated the remarkable potential of Deep Convolutional Neural Networks (DCNNs), which seem to exceed state-of-the-art performance in new domains weekly, especially on the sorts of very difficult perceptual discrimination tasks that skeptics thought would remain beyond the reach of artificial intelligence. However, it has proven difficult to explain why DCNNs perform so well. In philosophy of mind, empiricists have long suggested that complex cognition is based on information derived from sensory experience, often (...) appealing to a faculty of abstraction. Rationalists have frequently complained, however, that empiricists never adequately explained how this faculty of abstraction actually works. In this paper, I tie these two questions together, to the mutual benefit of both disciplines. I argue that the architectural features that distinguish DCNNs from earlier neural networks allow them to implement a form of hierarchical processing that I call “transformational abstraction”. Transformational abstraction iteratively converts sensory-based representations of category exemplars into new formats that are increasingly tolerant to “nuisance variation” in input. Reflecting upon the way that DCNNs leverage a combination of linear and non-linear processing to efficiently accomplish this feat allows us to understand how the brain is capable of bi-directional travel between exemplars and abstractions, addressing longstanding problems in empiricist philosophy of mind. I end by considering the prospects for future research on DCNNs, arguing that rather than simply implementing 80s connectionism with more brute-force computation, transformational abstraction counts as a qualitatively distinct form of processing ripe with philosophical and psychological significance, because it is significantly better suited to depict the generic mechanism responsible for this important kind of psychological processing in the brain. (shrink)

In the cognitive, computational, and neuro-sciences, practitioners often reason about what computational models represent or learn, as well as what algorithm is instantiated. The putative goal of such reasoning is to generalize claims about the model in question, to claims about the mind and brain, and the neurocognitive capacities of those systems. Such inference is often based on a model’s performance on a task, and whether that performance approximates human behavior or brain activity. Here we demonstrate how such argumentation problematizes (...) the relationship between models and their targets; we place emphasis on artificial neural networks (ANNs), though any theory-brain relationship that falls into the same schema of reasoning is at risk. In this paper, we model inferences from ANNs to brains and back within a formal framework — metatheoretical calculus — in order to initiate a dialogue on both how models are broadly understood and used, and on how to best formally characterize them and their functions. To these ends, we express claims from the published record about models’ successes and failures in first-order logic. Our proposed formalization describes the decision-making processes enacted by scientists to adjudicate over theories. We demonstrate that formalizing the argumentation in the literature can uncover potential deep issues about how theory is related to phenomena. We discuss what this means broadly for research in cognitive science, neuroscience, and psychology; what it means for models when they lose the ability to mediate between theory and data in a meaningful way; and what this means for the metatheoretical calculus our fields deploy when performing high-level scientific inference. (shrink)

The article argues that our concepts are deeply rooted in the architecture of visual processing. The argument is based on evidence provided by two seemingly very distant theories of mind together with two sorts of corresponding visions: Freud’s theory of dreams, which suggests oneiric visions represent our thoughts and the mechanical model of the mind developed in the context of computer science. As will be argued, Freud’s findings are in fact supported by advances in this field, in particular by deep (...) convolutional neural networks (DCNNs) which mirror the activity of visual cortex, producing visions strikingly similar to dreams. An in-depth analysis of such images, supported by insights from empiricism and conceptual metaphor theory, reveals that they represent visual universals, as well as more fragmentary notions pertaining to features, and complete abstractions, such as those found in language and in mathematics. This finding points towards a more comprehensive thesis about the links of vision to reflection: the crucial insight that will be developed and defended in this article is that the architecture of visual processing is the basis of the conceptual structures that underpin cognition. (shrink)

I address whether neural networks perform computations in the sense of computability theory and computer science. I explicate and defend
the following theses. (1) Many neural networks compute—they perform computations. (2) Some neural networks compute in a classical way.
Ordinary digital computers, which are very large networks of logic gates, belong in this class of neural networks. (3) Other neural networks
compute in a non-classical way. (4) Yet other neural networks (...) do not perform computations. Brains may well fall into this last class. (shrink)

This paper explores the structural mismatch problem between physical and phenomenal properties, where the similarity relations we experience among phenomenal properties lack corresponding relations in the physical domain. I introduce a new understanding of this problem via the Uniformity Principle: for any set of dimensions used to determine phenomenal similarities, there must be a consistently applied set of physical dimensions generating the same pattern of similarity relations. I then assess the potential of recent machine learning models, specifically graph neural (...) networks, to resolve this problem, as proposed by Epstein. By examining how these models generate sensory maps, I argue that the dimensions they adopt violate the Uniformity Principle in two ways: impure dimensions, where subjective responses affect the physical dimensions used, and non-uniform dimensions, where the applied dimensions vary inconsistently. These issues show that current machine learning models fail to establish a systematic correspondence between physical and phenomenal properties. (shrink)

Many kinds of creativity result from combination of mental representations. This paper provides a computational account of how creative thinking can arise from combining neural patterns into ones that are potentially novel and useful. We defend the hypothesis that such combinations arise from mechanisms that bind together neural activity by a process of convolution, a mathematical operation that interweaves structures. We describe computer simulations that show the feasibility of using convolution to produce emergent patterns of neural activity (...) that can support cognitive and emotional processes underlying human creativity. (shrink)

Despite their successes at prediction and classification, deep neural networks (DNNs) are often claimed to fail when it comes to providing any understanding of real-world phenomena. However, recently, some authors have argued that DNNs can provide such understanding. To resolve this controversy, I first examine under which conditions DNNs provide humans with explanatory understanding in a clearly defined sense that refers to a simple setting. I adopt a systematic approach that draws on theories of explanation and explanatory understanding, (...) but avoid dependence on any specific account by developing broad conditions of explanatory understanding that leave space for filling in the details in several alternative ways. I argue that the conditions are difficult to satisfy however these details are filled in. The main problem is that, to provide explanatory understanding in the sense I have defined, a DNN has to contain an explanation, and scientists typically do not know whether it does. Accordingly, they cannot feel committed to the explanation or use it, which means that other conditions of explanatory understanding are not satisfied. Still, in some attenuated senses, the conditions can be fulfilled. To complete my conciliatory project, I further show that my results so far are compatible with using DNNs to infer explanatorily relevant information in a thorough investigation. This is what the more optimistic literature on DNNs has focused on. In sum, then, the significance of DNNs for understanding real-world systems depends on what it means to say that they provide understanding, and on how humans use them. (shrink)

Deep neural networks (DNNs) provide a useful computational framework for constructing cognitive models of emotion understanding. This paper provides a focused discussion of the use of DNNs in this context. It begins by defining three key components of emotion understanding – perception, prediction, and regulation – and discussing how each can be modelling using different deep learning architectures. It continues by positioning what DNN models can contribute to affective science in relation to important existing theoretical perspectives, including both (...) domain-general frameworks like Bayesian cognitive modelling, and domain-specific frameworks, such as the theory of constructed emotion. The paper highlights both the strengths and limitations of DNNs as cognitive models and provides guidance for how to capitalise on the former while mitigating the latter. (shrink)

This paper introduces a new conceptual framework, the Resonance Neural Network (感應神經網), redefining resonance (感應) beyond its traditional interpretations in philosophy and affect theory. While classical accounts of resonance are often aligned with affect—understood as pre-reflective emotional or bodily responses—this study advances a different perspective: resonance as the pre-cognitive vibration that initiates creative spirit and leads to practical realization. The Resonance Neural Network is defined as the capacity of the human brain–mind system to sense invisible flows of energy, (...) meaning, and relational patterns, and to transform such subtle signals into creative cognition and action. Intuition, “gut feelings,” and déjà vu are not dismissed as irrational impressions, but instead recognized as manifestations of an underlying neural-philosophical resonance circuit. This framework positions resonance not as mere inspiration, emotion, or affect, but as the first vibration of creative spirit, which becomes strengthened when structured through thought and translated into willful action. In doing so, it bridges pre-rational sensitivity with conscious creativity, offering a new foundation for understanding human creation, branding philosophy, and consciousness studies. By articulating the Resonance Neural Network as a distinct conceptual innovation, this paper lays the groundwork for interdisciplinary dialogue across philosophy, neuroscience, creativity studies, and organizational practice. It further proposes that resonance serves as the seed of Founding Spirit (hereafter FoundSpirit), thereby providing both an ontological and practical framework for exploring how pre-cognitive resonance shapes human will, endurance, and the pursuit of meaningful creation. (shrink)

Neural networks have long been used to study linguistic phenomena spanning the domains of phonology, morphology, syntax, and semantics. Of these domains, semantics is somewhat unique in that there is little clarity concerning what a model needs to be able to do in order to provide an account of how the meanings of complex linguistic expressions, such as sentences, are understood. We argue that one thing such models need to be able to do is generate predictions about which (...) further sentences are likely to follow from a given sentence; these define the sentence's “inferential role.” We then show that it is possible to train a tree-structured neural network model to generate very simple examples of such inferential roles using the recently released Stanford Natural Language Inference (SNLI) dataset. On an empirical front, we evaluate the performance of this model by reporting entailment prediction accuracies on a set of test sentences not present in the training data. We also report the results of a simple study that compares human plausibility ratings for both human-generated and model-generated entailments for a random selection of sentences in this test set. On a more theoretical front, we argue in favor of a revision to some common assumptions about semantics: understanding a linguistic expression is not only a matter of mapping it onto a representation that somehow constitutes its meaning; rather, understanding a linguistic expression is mainly a matter of being able to draw certain inferences. Inference should accordingly be at the core of any model of semantic cognition. (shrink)

This paper proposes several recurrent neural network-based models for recognizing requisite and effectuation parts in Legal Texts. Firstly, we propose a modification of BiLSTM-CRF model that allows the use of external features to improve the performance of deep learning models in case large annotated corpora are not available. However, this model can only recognize RE parts which are not overlapped. Secondly, we propose two approaches for recognizing overlapping RE parts including the cascading approach which uses the sequence of BiLSTM-CRF (...) models and the unified model approach with the multilayer BiLSTM-CRF model and the multilayer BiLSTM-MLP-CRF model. Experimental results on two Japan law RRE datasets demonstrated advantages of our proposed models. For the Japanese National Pension Law dataset, our approaches obtained an \ score of 93.27% and exhibited a significant improvement compared to previous approaches. For the Japan Civil Code RRE dataset which is written in English, our approaches produced an \ score of 78.24% in recognizing RE parts that exhibited a significant improvement over strong baselines. In addition, using external features and in-domain pre-trained word embeddings also improved the performance of RRE systems. (shrink)

Human decision making shows systematic simplifications and deviations from the tenets of rationality (‘heuristics’) that may lead to suboptimal decisional outcomes (‘cognitive biases’). There are currently three prevailing theoretical perspectives on the origin of heuristics and cognitive biases: a cognitive-psychological, an ecological and an evolutionary perspective. However, these perspectives are mainly descriptive and none of them provides an overall explanatory framework for the underlying mechanisms of cognitive biases. To enhance our understanding of cognitive heuristics and biases we propose a (...) class='Hi'>neural network framework for cognitive biases, which explains why our brain systematically tends to default to heuristic (‘Type 1’) decision making. We argue that many cognitive biases arise from intrinsic brain mechanisms that are fundamental for the working of biological neural networks. In order to substantiate our viewpoint, we discern and explain four basic neural network principles: (1) Association, (2) Compatibility (3) Retainment, and (4) Focus. These principles are inherent to (all) neural networks which were originally optimized to perform concrete biological, perceptual, and motor functions. They form the basis for our inclinations to associate and combine (unrelated) information, to prioritize information that is compatible with our present state (such as knowledge, opinions and expectations), to retain given information that sometimes could better be ignored, and to focus on dominant information while ignoring relevant information that is not directly activated. The supposed mechanisms are complementary and not mutually exclusive. For different cognitive biases they may all contribute in varying degrees to distortion of information. The present viewpoint not only complements the earlier three viewpoints, but also provides a unifying and binding framework for many cognitive bias phenomena. (shrink)

In this study, an accurate convergence time of the supertwisting algorithm is proposed to build up a framework for nonaffine nonlinear systems’ finite-time control. The convergence time of the STA is provided by calculating the solution of a differential equation instead of constructing Lyapunov function. Therefore, precise convergence time is presented instead of estimation of the upper bound of the algorithm’s reaching time. Regardless of affine or nonaffine nonlinear systems, supertwisting control provides a general solution based on virtual control law (...) skill ensuring the output of the systems converges to the origin point at exact time. Benchmark tests are simulated to demonstrate the effectiveness and efficiency of the algorithm. (shrink)

The predominance of machine learning based techniques in cognitive neuroscience raises a host of philosophical and methodological concerns. Given the messiness of neural activity, modellers must make choices about how to structure their raw data to make inferences about encoded representations. This leads to a set of standard methodological assumptions about when abstraction is appropriate in neuroscientific practice. Yet, when made uncritically these choices threaten to bias conclusions about phenomena drawn from data. Contact between the practices of multivariate pattern (...) analysis and philosophy of science can help to illuminate the conditions under which we can use artificial neural networks to better understand neural mechanisms. This paper considers a specific technique for MVPA called representational similarity analysis. I develop a theoretically-informed account of RSA that draws on early connectionist research and work on idealization in the philosophy of science. By bringing a philosophical account of cognitive modelling in conversation with RSA, this paper clarifies the practices of neuroscientists and provides a generalizable framework for using artificial neural networks to study neural mechanisms in the brain. (shrink)

As a type of evidence glass can be very useful contact trace material in a wide range of offences including burglaries and robberies, hit-and-run accidents, murders, assaults, ram-raids, criminal damage and thefts of and from motor vehicles. All of that offer the potential for glass fragments to be transferred from anything made of glass which breaks, to whoever or whatever was responsible. Variation in manufacture of glass allows considerable discrimination even with tiny fragments. In this study, we worked glass classification (...) and testing of artificial neural network model created by the JustNN. The aim of the study is help investigator in identifying the type of glass found in arena of the crime. The Neural Network model was trained and validated using the type of glass dataset. The accuracy of model in predicting the type of glass reached 96.7%. Thus neural network is suitable for predicating type of glasses. (shrink)

Diabetes is one of the most common diseases worldwide where a cure is not found for it yet. Annually it cost a lot of money to care for people with diabetes. Thus the most important issue is the prediction to be very accurate and to use a reliable method for that. One of these methods is using artificial intelligence systems and in particular is the use of Artificial Neural Networks (ANN). So in this paper, we used artificial (...) class='Hi'>neural networks to predict whether a person is diabetic or not. The criterion was to minimize the error function in neural network training using a neural network model. After training the ANN model, the average error function of the neural network was equal to 0.01 and the accuracy of the prediction of whether a person is diabetics or not was 87.3%. (shrink)

Choice Outstanding Academic Title, 1996. In hundreds of articles by experts from around the world, and in overviews and "road maps" prepared by the editor, The Handbook of Brain Theory and Neural Networkscharts the immense progress made in recent years in many specific areas related to two great questions: How does the brain work? and How can we build intelligent machines? While many books have appeared on limited aspects of one subfield or another of brain theory and neural (...) networks, the Handbookcovers the entire sweep of topics—from detailed models of single neurons, analyses of a wide variety of biological neural networks, and connectionist studies of psychology and language, to mathematical analyses of a variety of abstract neural networks, and technological applications of adaptive, artificial neural networks. The excitement, and the frustration, of these topics is that they span such a broad range of disciplines including mathematics, statistical physics and chemistry, neurology and neurobiology, and computer science and electrical engineering as well as cognitive psychology, artificial intelligence, and philosophy. Thus, much effort has gone into making the Handbookaccessible to readers with varied backgrounds while still providing a clear view of much of the recent, specialized research in specific topics. The heart of the book, part III, comprises of 267 original articles by leaders in the various fields, arranged alphabetically by title. Parts I and II, written by the editor, are designed to help readers orient themselves to this vast range of material. Part I, Background, introduces several basic neural models, explains how the present study of brain theory and neural networks integrates brain theory, artificial intelligence, and cognitive psychology, and provides a tutorial on the concepts essential for understanding neural networks as dynamic, adaptive systems. Part II, Road Maps, provides entry into the many articles of part III through an introductory "Meta-Map" and twenty-three road maps, each of which tours all the Part III articles on the chosen theme. (shrink)

We present the basic abstract of the newly obtained results on class of non-layered artificial neural networks.

Deep neural networks (DNNs) have had extraordinary successes in classifying photographic images of objects and are often described as the best models of biological vision. This conclusion is largely based on three sets of findings: (1) DNNs are more accurate than any other model in classifying images taken from various datasets, (2) DNNs do the best job in predicting the pattern of human errors in classifying objects taken from various behavioral datasets, and (3) DNNs do the best job (...) in predicting brain signals in response to images taken from various brain datasets (e.g., single cell responses or fMRI data). However, these behavioral and brain datasets do not test hypotheses regarding what features are contributing to good predictions and we show that the predictions may be mediated by DNNs that share little overlap with biological vision. More problematically, we show that DNNs account for almost no results from psychological research. This contradicts the common claim that DNNs are good, let alone the best, models of human object recognition. We argue that theorists interested in developing biologically plausible models of human vision need to direct their attention to explaining psychological findings. More generally, theorists need to build models that explain the results of experiments that manipulate independent variables designed to test hypotheses rather than compete on making the best predictions. We conclude by briefly summarizing various promising modeling approaches that focus on psychological data. (shrink)

In the field of applied computer research, the problem of the reinforcement of existing inequalities through the processing of “big data” in neural networks is typically addressed via concepts of representation and fairness. These approaches, however, tend to overlook the limits of the liberal antidiscrimination discourse, which are well established in critical theory. In this paper, I address these limits and propose a different framework for understanding technologically amplified oppression departing from the notion of “mute compulsion” (Marx), a (...) specifically modern form of power based on the social abstraction of wage labor in market exchange. I begin with a reconstruction of the process of technological abstraction in automated pattern recognition, after which I summarize the conceptional shortcomings of representational fairness discourse. In contrast, I demonstrate how the social reproduction of exploitation is conceptualized in critical theory as being mediated through a process of social abstraction, defined as a social practice of reification that manifest in fetishization. To avoid economistic shortcomings, I contextualize the argument of social abstraction against the backdrop of social reproduction theory, which takes the juncture of various historical forms of oppression into account. I conclude by elaborating how technological abstraction corresponds to the problem of mute compulsion by replicating processes of social abstraction. (shrink)

Psychologically faithful deep neural networks (DNNs) could be constructed by training with psychophysics data. Moreover, conventional DNNs are mostly monocular vision based, whereas the human brain relies mainly on binocular vision. DNNs developed as smaller vision agent networks associated with fundamental and less intelligent visual activities, can be combined to simulate more intelligent visual activities done by the biological brain.

Should developers be held responsible for the predictions of their neural networks—and if not, does that introduce a responsibility gap? The claim that neural networks introduce a responsibility gap has seen significant pushback, with philosophers arguing that the gap can be bridged, or did not exist in the first place. We show how the responsibility gap turns on whether we can distinguish between foreseeable and unforeseeable neural network predictions. Empirical facts about neural networks (...) tell us we cannot, which seems to force developers to either assume full responsibility or no responsibility at all, introducing a responsibility gap—unless, of course, the same empirical facts hold true of humans, in which case there is no gap, but the trouble is simply with the classical notion of responsibility. We revisit and revise Mele’s Zygote, as well as the famous Palsgraf case, and argue that in fact, what complicates responsibility assignment for neural networks also complicates responsibility assignment for humans, and humans seem to confront us with the same all-or-nothing dilemma. Thus, we agree there is no technology-induced responsibility gap (there was no gap in the first place), but for slightly different reasons than our predecessors. (shrink)

The ontology of social objects and facts remains a field of continued controversy. This situation complicates the life of social scientists who seek to make predictive models of social phenomena. For the purposes of modelling a social phenomenon, we would like to avoid having to make any controversial ontological commitments. The overwhelming majority of models in the social sciences, including statistical models, are built upon ontological assumptions that can be questioned. Recently, however, artificial neural networks have made their (...) way into the social sciences, raising the question whether they can avoid controversial ontological assumptions. ANNs are largely distinguished from other statistical and machine learning techniques by being a representation-learning technique. That is, researchers can let the neural networks select which features of the data to use for internal representation instead of imposing their preconceptions. On this basis, I argue that neural networks can avoid ontological assumptions to a greater degree than common statistical models in the social sciences. I then go on, however, to establish that ANNs are not ontologically innocent either. The use of ANNs in the social sciences introduces ontological assumptions typically in at least two ways, via the input and via the architecture. (shrink)

We propose a new interpretability method for neural networks, which is based on a novel mathematico-philosophical theory of reasons. Our method computes a vector for each neuron, called its reasons vector. We then can compute how strongly this reasons vector speaks for various propositions, e.g., the proposition that the input image depicts digit 2 or that the input prompt has a negative sentiment. This yields an interpretation of neurons, and groups thereof, that combines a logical and a Bayesian (...) perspective, and accounts for polysemanticity (i.e., that a single neuron can figure in multiple concepts). We show, both theoretically and empirically, that this method is: (1) grounded in a philosophically established notion of explanation, (2) uniform, i.e., applies to the common neural network architectures and modalities, (3) scalable, since computing reason vectors only involves forward-passes in the neural network, (4) faithful, i.e., intervening on a neuron based on its reason vector leads to expected changes in model output, (5) correct in that the model's reasons structure matches that of the data source, (6) trainable, i.e., neural networks can be trained to improve their reason strengths, (7) useful, i.e., it delivers on the needs for interpretability by increasing, e.g., robustness and fairness. (shrink)

. Interpreted dynamical systems are dynamical systems with an additional interpretation mapping by which propositional formulas are assigned to system states. The dynamics of such systems may be described in terms of qualitative laws for which a satisfaction clause is defined. We show that the systems Cand CL of nonmonotonic logic are adequate with respect to the corresponding description of the classes of interpreted ordered and interpreted hierarchical systems, respectively. Inhibition networks, artificial neural networks, logic programs, and (...) evolutionary systems are instances of such interpreted dynamical systems, and thus our results entail that each of them may be described correctly and, in a sense, even completely by qualitative laws that obey the rules of a nonmonotonic logic system. (shrink)

This article presents Epistemic Spatialization as a new framework for investigating the interconnected patterns of biases when identifying objects with convolutional neural networks (convnets). It draws upon Foucault’s notion of spatialized knowledge to guide its method of enquiry. We argue that decisions involved in the creation of algorithms, alongside the labeling, ordering, presentation, and commercial prioritization of objects, together create a distorted “nomination of the visible”: they harden the visibility of some objects, make other objects excessively visible, and (...) consign yet others to permanent or haphazard invisibility. Our approach differs from those who focus on high-stakes misidentifications, such as errors tied to structural racism. Examining the far more dominant series of low-stakes mistakes shows the scope of errors, destabilizing the goal of image content identification with considerable societal impact. We explore these issues by closely examining the demonstration video of a popular convnet. This examination reveals an interlocking series of biases undermining the content identification process. The picture we paint is crucial for a better understanding of the errors that result as these convnets become further embedded in everyday products. The framework is valuable for critical work on computer vision, AI studies, and large-scale visual analysis. (shrink)

This work describes a mathematical concept of modelling field theory and its applications to a variety of problems, while offering a view of the relationships among mathematics, computational concepts in neural networks, semiotics, and concepts of mind in psychology and philosophy.

Deep neural networks (DNNs) have found many useful applications in recent years. Of particular interest have been those instances where their successes imitate human cognition and many consider artificial intelligences to offer a lens for understanding human intelligence. Here, we criticize the underlying conflation between the predictive and explanatory power of DNNs by examining the goals of modeling.

The article considers the problem of images and the role they play in our reflection turning to evidence provided by two seemingly very distant theories of mind together with two sorts of corresponding visions: dreams as analyzed by Freud who claimed that they are pictures of our thoughts, and their mechanical counterparts produced by neural networks designed for object recognition and classification. Freud’s theory of dreams has largely been ignored by philosophers interested in cognition, most of whom focused (...) solely on the linguistic incarnation of thoughts, but even though commonly neglected by respectable theories of thinking, dream images may prove to be the key to the black box of thought. As argued in this article, when seen from the right perspective and approached with the right set of questions, oneiric visions yield groundbreaking insights into the mechanism of how concepts and judgments are formed. Support for this conclusion comes from a tradition seemingly remote, if not opposed to psychoanalysis: the mechanical model of the mind conceived by information sciences and embodied in the form of artificial neural nets which mirror the activity of human visual cortex producing visions strikingly similar to those created by the sleeping mind. These purely mechanical, artificial ‘dreams’ constitute byproducts of algorithms designed for object recognition and classification, which, as I shall argue, reveals the true purpose of our own oneiric visual formations. Just like their mechanical counterparts produced by neural networks, condensations and displacements encountered in dreams are in fact visual universals. (shrink)

Intrauterine insemination is one of many treatments provided to infertility patients. Many factors such as, but not limited to, quality of semen, the age of a woman, and reproductive hormone levels contribute to infertility. Therefore, the aim of our study is to establish a statistical probability concerning the prediction of which groups of patients have a very good or poor prognosis for pregnancy after IUI insemination. For that purpose, we compare the results of two analyses: Cluster Analysis and Kohonen (...) class='Hi'>Neural Networks. The k-means algorithm from the clustering methods was the best to use for selecting patients with a good prognosis but the Kohonen Neural Networks was better for selecting groups of patients with the lowest chances for pregnancy. (shrink)

Paul Feyerabend recommended the methodological policy of proliferating competing theories as a means to uncovering new empirical data, and thus as a means to increase the empirical constraints that all theories must confront. Feyerabend's policy is here defended as a clear consequence of connectionist models of explanatory understanding and learning. An earlier connectionist "vindication" is criticized, and a more realistic and penetrating account is offered in terms of the computationally plastic cognitive profile displayed by neural networks with a (...) recurrent architecture. (shrink)

In Artificial Intelligence, Artificial Neural Networks are very accurate models in tasks such as classification and regression in the study of natural phenomena, but they are considered “black boxes” because they do not allow direct explanation of what they address. This paper reviews the possibility of scientific explanation from these models and concludes that other efforts are required to understand their inner workings. This poses challenges to access scientific explanation through their use, since the nature of Artificial (...) class='Hi'>Neural Networks makes it difficult at first instance the scientific understanding that can be extracted from them. (shrink)

Aberrations introduced by the atmospheric turbulence in large telescopes are compensated using adaptive optics systems, where the use of deformable mirrors and multiple sensors relies on complex control systems. Recently, the development of larger scales of telescopes as the E-ELT or TMT has created a computational challenge due to the increasing complexity of the new adaptive optics systems. The Complex Atmospheric Reconstructor based on Machine Learning is an algorithm based on artificial neural networks, designed to compensate the atmospheric (...) turbulence. During recent years, the use of GPUs has been proved to be a great solution to speed up the learning process of neural networks, and different frameworks have been created to ease their development. The implementation of CARMEN in different Multi-GPU frameworks is presented in this paper, along with its development in a language originally developed for GPU, like CUDA. This implementation offers the best response for all the presented cases, although its advantage of using more than one GPU occurs only in large networks. (shrink)

If artificial neural networks are ever to form the foundation for higher level cognitive behaviors in machines or to realize their full potential as explanatory devices for human cognition, they must show signs of autonomy, multifunction operation, and intersystem integration that are absent in most existing models. This model begins to address these issues by integrating predictive learning, sequence interleaving, and sequence creation components to simulate a spectrum of higher-order cognitive behaviors which have eluded the grasp of simpler (...) systems. Its capabilities are described based on simulations calling for increasing levels of functionality and are used to show how the model can progress from fundamental sequence learning and recall tasks to sophisticated behaviors such as an ability to solve simple mathematical expressions and a creative capacity for the formation and application of inductive rules. (shrink)