Brains, unlike artificial neural nets, use symbols to summarise and reason about perceptual input. But unlike symbolic AI, they “ground” the symbols in the data: the symbols have meaning in terms of data, not just meaning imposed by the outside user. If neural nets could be made to grow their own symbols in the way that brains do, there would be a good prospect of combining neural networks and symbolic AI, in such a way as (...) to combine the good features of each. The article argues the cluster analysis provides algorithms to perform the task, and that any solution to the task must be a form of cluster analysis. (shrink)

Assistive systems based on Artificial Intelligence (AI) are bound to reshape decision-making in all areas of society. One of the most intricate challenges arising from their implementation in high-stakes environments such as medicine concerns their frequently unsatisfying levels of explainability, especially in the guise of the so-called black-box problem: highly successful models based on deep learning seem to be inherently opaque, resisting comprehensive explanations. This may explain why some scholars claim that research should focus on rendering AI systems understandable, rather (...) than explainable. Yet, there is a grave lack of agreement concerning these terms in much of the literature on AI. We argue that the seminal distinction made by the philosopher and physician Karl Jaspers between different types of explaining and understanding in psychopathology can be used to promote greater conceptual clarity in the context of Machine Learning (ML). Following Jaspers, we claim that explaining and understanding constitute multi-faceted epistemic approaches that should not be seen as mutually exclusive, but rather as complementary ones as in and of themselves they are necessarily limited. Drawing on the famous example of Watson for Oncology we highlight how Jaspers’ methodology translates to the case of medical AI. Classical considerations from the philosophy of psychiatry can therefore inform a debate at the centre of current AI ethics, which in turn may be crucial for a successful implementation of ethically and legally sound AI in medicine. (shrink)

After people learn to sort objects into categories they see them differently. Members of the same category look more alike and members of different categories look more different. This phenomenon of within-category compression and between-category separation in similarity space is called categorical perception (CP). It is exhibited by human subjects, animals and neural net models. In backpropagation nets trained first to auto-associate 12 stimuli varying along a onedimensional continuum and then to sort them into 3 categories, CP arises (...) as a natural side-effect because of four factors: (1) Maximal interstimulus separation in hidden-unit space during autoassociation learning, (2) movement toward linear separability during categorization learning, (3) inverse-distance repulsive force exerted by the between-category boundary, and (4) the modulating effects of input iconicity, especially in interpolating CP to untrained regions of the continuum. Once similarity space has been "warped" in this way, the compressed and separated "chunks" have symbolic labels which could then be combined into symbol strings that constitute propositions about objects. The meanings of such symbolic representations would be "grounded" in the system's capacity to pick out from their sensory projections the object categories that the propositions were about. (shrink)

We work with a large spatialized array of individuals in an environment of drifting food sources and predators. The behavior of each individual is generated by its simple neural net; individuals are capable of making one of two sounds and are capable of responding to sounds from their immediate neighbors by opening their mouths or hiding. An individual whose mouth is open in the presence of food is “fed” and gains points; an individual who fails to hide when a (...) predator is present is “hurt” by losing points. Opening mouths, hiding, and making sounds each exact an energy cost. There is no direct evolutionary gain for acts of cooperation or “successful communication” per se. In such an environment we start with a spatialized array of neural nets with randomized weights. Using standard learning algorithms, our individuals “train up” on the behavior of successful neighbors at regular intervals. Given that simple setup, will a community of neural nets evolve a simple language for signaling the presence of food and predators? With important qualifications, the answer is “yes.” In a simple spatial environment, pursuing individualistic gains and using partial training on successful neighbors, randomized neural nets can learn to communicate. (shrink)

Some of the features of animal and human categorical perception (CP) for color, pitch and speech are exhibited by neural net simulations of CP with one-dimensional inputs: When a backprop net is trained to discriminate and then categorize a set of stimuli, the second task is accomplished by "warping" the similarity space (compressing within-category distances and expanding between-category distances). This natural side-effect also occurs in humans and animals. Such CP categories, consisting of named, bounded regions of similarity space, may (...) be the ground level out of which higher-order categories are constructed; nets are one possible candidate for the mechanism that learns the sensorimotor invariants that connect arbitrary names (elementary symbols?) to the nonarbitrary shapes of objects. This paper examines how and why such compression/expansion effects occur in neural nets. (shrink)

1.1 The predominant approach to cognitive modeling is still what has come to be called "computationalism" (Dietrich 1990, Harnad 1990b), the hypothesis that cognition is computation. The more recent rival approach is "connectionism" (Hanson & Burr 1990, McClelland & Rumelhart 1986), the hypothesis that cognition is a dynamic pattern of connections and activations in a "neural net." Are computationalism and connectionism really deeply different from one another, and if so, should they compete for cognitive hegemony, or should they collaborate? (...) These questions will be addressed here, in the context of an obstacle that is faced by computationalism (as well as by connectionism if it is either computational or seeks cognitive hegemony on its own): The symbol grounding problem (Harnad 1990). (shrink)

A crucial question for artificial cognition systems is what meaning is and how it arises. In pursuit of that question, this paper extends earlier work in which we show that emergence of simple signaling in biologically inspired models using arrays of locally interactive agents. Communities of "communicators" develop in an environment of wandering food sources and predators using any of a variety of mechanisms: imitation of successful neighbors, localized genetic algorithms and partial neural net training on successful neighbors. Here (...) we focus on environmental variability, comparing results for environments with (a) constant resources, (b) random resources, and (c) cycles of "boom and bust." In both simple and complex models across all three mechanisms of strategy change, the emergence of communication is strongly favored by cycles of "boom and bust." These results are particularly intriguing given the importance of environmental variability in fields as diverse as psychology, ecology and cultural anthropology. (shrink)

A possible relation between Derrida's deconstruction of metaphysics and connectionism is explored by considering diffeacuterance in neural nets terms. First diffeacuterance, as the crossing of Saussurian difference and Freudian deferral, is modeled and then the fuller 'sheaf of diffeacuterance is taken up. The metaphysically conceived brain has two versions: in the traditional computational version the brain processes information like a computer and in the connectionist version the brain computes input vector to output vector transformations non-symbolically. The 'deconstructed brain' (...) neither processes information nor computes functions but is spontaneously economical. (shrink)

The goal of philosophy of information is to understand what information is, how it operates, and how to put it to work. But unlike ‘information’ in the technical sense of information theory, what we are interested in is meaningful information. To understand the nature and dynamics of information in this sense we have to understand meaning. What we offer here are simple computational models that show emergence of meaning and information transfer in randomized arrays of neural nets. These (...) we take to be formal instantiations of a tradition of theories of meaning as use. What they offer, we propose, is a glimpse into the origin and dynamics of at least simple forms of meaning and information transfer as properties inherent in behavioral coordination across a community. (shrink)

The COVID-19 pandemic heavily influenced human life by constricting human social activity. Following the spread of the pandemic, humans did not have a choice but to change their lifestyles. There has been much change in the field of education, which has led to schools hosting online classes as an alternative to face-to-face classes. However, the concentration level is lowered in the online learning class, and the student’s learning rate decreases. We devise a framework for recognizing and estimating students’ concentration levels (...) to help lecturers. Previous studies have a limitation in that they classified attention levels using only discrete states. Due to the partial information from discrete states, the concentration levels could not be recognized well. This research aims to estimate more subtle levels as specified states by using a minimum amount of body movement data. The deep neural network is used to continuously recognize the human concentration model, and the concentration levels can be predicted and estimated by the Kalman filter. Using our framework, we successfully extracted the concentration levels, which can aid lecturers and can be expanded to other areas. To implement the framework, we recruited participants to take online classes. Data were collected and preprocessed using pose points, and an accuracy of 90.62 % was calculated by predicting the concentration level using the framework. Furthermore, the concentration level was approximated based on the Kalman filter. We found that webcams can be used to quantitatively measure student concentration when conducting online classes. Our framework is a great help for instructors to measure concentration levels, which can increase the learning efficiency. As a future work of this study, if emotion data and skin thermal data are comprehensively considered, a student’s concentration level can be measured more precisely. (shrink)

This article traces the relationship between neoliberal thought and neural networks through the work of Friedrich Hayek, Donald O. Hebb, and Frank Rosenblatt. For all three, networked systems could accomplish acts of evolution, change, and learning impossible for individual neurons or subjects—minds, machines, and economies could therefore all autonomously evolve and adapt without government. These three figures, I argue, were also symptoms of a broader reconceptualization of reason, decision making, and “freedom” in relation to the state and technology that (...) occurred throughout the 1950s–1970s. I also argue that this genealogy of decision-making underpins contemporary relations between machine learning, reactionary politics, and neoliberal economics. (shrink)

The goal of philosophy of information is to understand what information is, how it operates, and how to put it to work. But unlike ‘information’ in the technical sense of information theory, what we are interested in is meaningful information. To understand the nature and dynamics of information in this sense we have to understand meaning. What we offer here are simple computational models that show emergence of meaning and information transfer in randomized arrays of neural nets. These (...) we take to be formal instantiations of a tradition of theories of meaning as use. What they offer, we propose, is a glimpse into the origin and dynamics of at least simple forms of meaning and information transfer as properties inherent in behavioral coordination across a community. (shrink)

Early and accurate diagnosis of glaucoma is critical for avoiding human vision deterioration and preventing blindness. A deep-neural-network model has been developed for the diagnosis of glaucoma based on Heidelberg retina tomography, called “Seeking Common Features and Reserving Differences Net” to make full use of the HRT data. In this work, the proposed SCRD-Net model achieved an area under the curve of 94.0%. For the two HRT image modalities, the model sensitivities were 91.2% and 78.3% at specificities of 0.85 (...) and 0.95, respectively. These results demonstrate a significant improvement over earlier results. In addition, we visualized the network outputs to develop an interpretation of the learned mechanism for discriminating glaucoma and normal images. Thus, the SCRD-Net can be an effective diagnostic indicator of glaucoma during clinical screening. To facilitate SCRD-Net utilization by the scientific community, the code implementation will be made publicly available. (shrink)

We describe and try to motivate our project to build systems using both a knowledge based and a neural network approach. These two approaches are used at different stages in the solution of a problem, instead of using knowledge bases exclusively on some problems, and neural nets exclusively on others. The knowledge base (KB) is defined first in a declarative, symbolic language that is easy to use. It is then compiled into an efficient neural network (NN) (...) representation, run, and the results from run time and (eventually) from learning are decompiled to a symbolic description of the knowledge contained in the network. After inspecting this recovered knowledge, a designer would be able to modify the KB and go through the whole cycle of compiling, running, and decompiling again. The central question with which this project is concerned is, therefore, How do we go from a KB to an NN, and back again? We are investigating this question by building tools consisting of a repertoire of language/translation/network types, and trying them on problems in a variety of domains. (shrink)

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)

Abstract:In her 2002 essay, "Anthropocentrism, Artificial Intelligence, and Moral Network Theory: An Ecofeminist Perspective," Victoria Davion points out, utilizing Val Plumwood's ecofeminist analysis, the faulty anthropocentric, logocentric assumptions made both within the artificial intelligence (AI) community, generating serious problems in the effort to build "intelligent" machines, and in moral philosophy, its "rule-based picture of moral reasoning" (169) coming under fire from the emerging field of neural net research. Davion demonstrates prescience regarding the direction in which both disciplines eventually move, (...) as they learn important "lessons from nature": that intelligence and moral reasoning are widely distributed throughout the Biosphere and are not based upon what has been taken as paradigmatic—the reductive, linear logic, abstracted from all context, characteristic of only one possible way of approaching the world. I present updates regarding artificial intelligence, neuropsychology, and the philosophical analysis of anthropocentrism, affirming that directing open, respectful attention toward the Other in the real, living world will eventually provide us with the ontological foundation for a nonanthropocentric ethics capable of sustaining truly intelligent and moral ways of living. (shrink)

“The physics of representation” aims to define the word “representation” as used in the neurosciences, argue that such representations as described in neuroscience are related to and usefully illuminated by the representations generated by modern neural networks, and establish that these entities are “representations in good standing”. We suggest that Poldrack succeeds in, exposes some tensions between the broad use of the term in neuroscience and the narrower class of entities that he identifies in the end, and between the (...) meaning of “representation” in neuroscience and in psychology in, and fails in. This results in some hard choices: give up on the broad scope of the term in neuroscience or continue to embrace the broad, psychologically inflected sense of the term, and deny the entities generated by neural nets are representations in the relevant sense. (shrink)