Explore the vast range of titles available.

A thermodynamically motivated neural network model is described that self-organizes to transport charge associated with internal and external potentials while in contact with a thermal reservoir. The model integrates techniques for rapid, large-scale, reversible, conservative equilibration of node states and slow, small-scale, irreversible, dissipative adaptation of the edge states as a means to create multiscale order. All interactions in the network are local and the network structures can be generic and recurrent. Isolated networks show multiscale dynamics, and externally driven networks evolve to efficiently connect external positive and negative potentials. The model integrates concepts of conservation, potentiation, fluctuation, dissipation, adaptation, equilibration and causation to illustrate the thermodynamic evolution of organization in open systems. A key conclusion of the work is that the transport and dissipation of conserved physical quantities drives the self-organization of open thermodynamic systems.

We describe a model system—a thermodynamic state machine network—comprising a network of probabilistic, stateful automata that equilibrate according to Boltzmann statistics, exchange codes over unweighted bi-directional edges, update a state transition memory to learn transitions between network ground states, and minimize an action associated with fluctuation trajectories. The model is grounded in four postulates concerning self-organizing, open thermodynamic systems—transport-driven self-organization, scale-integration, input-functionalization, and active equilibration. After sufficient exposure to periodically changing inputs, a diffusive-to-mechanistic phase transition emerges in the network dynamics. The evolved networks show spatial and temporal structures that look much like spiking neural networks, although no such structures were incorporated into the model. Our main contribution is the articulation of the postulates, the development of a thermodynamically motivated methodology addressing them, and the resulting phase transition. As with other machine learning methods, the model is limited by its scalability, generality, and temporality. We use limitations to motivate the development of thermodynamic computers—engineered, thermodynamically self-organizing systems—and comment on efforts to realize them in the context of this work. We offer a different philosophical perspective, thermodynamicalism, addressing the limitations of the model and machine learning in general.

Mental imagery and planning are important aspects of cognitive behaviour. Being able to predict outcomes through mental simulation can increase environmental fitness and reduce uncertainty. Such predictions reduce surprise and fit with thermodynamically driven theories of brain function by attempting to reduce entropy. In the present work, the authors tested these ideas in a predator–prey scenario where agents with a limited energy budget had to maximise food intake, while avoiding a predator. Forward planning agents, with the ability to mentalise, to Actor Critic agents that do not plan beyond the current state were also compared. The authors show that the ability to mentalise has distinct advantages when in noisy, uncertain stimuli. These advantages are even more prevalent when tested in the real world on physical robots. The authors’ results highlight the importance of taking into consideration mental imagery and embodiment when constructing artificial cognitive systems.

A thermodynamically motivated neural network model is described that self-organizes to transport charge associated with internal and external potentials while in contact with a thermal reservoir. The model integrates techniques for rapid, large-scale, reversible, conservative equilibration of node states and slow, small-scale, irreversible, dissipative adaptation of the edge states as a means to create multiscale order. All interactions in the network are local and the network structures can be generic and recurrent. Isolated networks show multiscale dynamics, and externally driven networks evolve to efficiently connect external positive and negative potentials. The model integrates concepts of conservation, potentiation, fluctuation, dissipation, adaptation, equilibration and causation to illustrate the thermodynamic evolution of organization in open systems. A key conclusion of the work is that the transport and dissipation of conserved physical quantities drives the self-organization of open thermodynamic systems.

We propose a model that emulates saccades, the rapid movements of the eye, called the Error Saccade Model, based on the prediction error of the Predictive Vision Model (PVM). The Error Saccade Model carries out movements of the model's field of view to regions with the highest prediction error. Comparisons of the Error Saccade Model on Predictive Vision Models with and without a fovea show that a fovea-like structure in the input level of the PVM improves the Error Saccade Model's ability to pursue detailed objects in its view. We hypothesize that the improvement is due to poorer resolution in the periphery causing higher prediction error when an object passes, triggering a saccade to the next location.

We demonstrate an improved vision system that learns a model of its environment using a self-supervised, predictive learning method. The system includes a pan-tilt camera, a foveated visual input, a saccading reflex to servo the foveated region to areas high prediction error, input frame transformation synced to the camera motion, and a recursive, hierachical machine learning technique based on the Predictive Vision Model. In earlier work, which did not integrate camera motion into the vision model, prediction was impaired and camera movement suffered from undesired feedback effects. Here we detail the integration of camera motion into the predictive learning system and show improved visual prediction and saccadic behavior. From these experiences, we speculate on the integration of additional sensory and motor systems into self-supervised, predictive learning models.

Understanding visual reality involves acquiring common-sense knowledge about countless regularities in the visual world, e.g., how illumination alters the appearance of objects in a scene, and how motion changes their apparent spatial relationship. These regularities are hard to label for training supervised machine learning algorithms; consequently, algorithms need to learn these regularities from the real world in an unsupervised way. We present a novel network meta-architecture that can learn world dynamics from raw, continuous video. The components of this network can be implemented using any algorithm that possesses three key capabilities: prediction of a signal over time, reduction of signal dimensionality (compression), and the ability to use supplementary contextual information to inform the prediction. The presented architecture is highly-parallelized and scalable, and is implemented using localized connectivity, processing, and learning. We demonstrate an implementation of this architecture where the components are built from multi-layer perceptrons. We apply the implementation to create a system capable of stable and robust visual tracking of objects as seen by a moving camera. Results show performance on par with or exceeding state-of-the-art tracking algorithms. The tracker can be trained in either fully supervised or unsupervised-then-briefly-supervised regimes. Success of the briefly-supervised regime suggests that the unsupervised portion of the model extracts useful information about visual reality. The results suggest a new class of AI algorithms that uniquely combine prediction and scalability in a way that makes them suitable for learning from and --- and eventually acting within --- the real world.

There has been great progress in understanding of anatomical and functional microcircuitry of the primate cortex. However, the fundamental principles of cortical computation - the principles that allow the visual cortex to bind retinal spikes into representations of objects, scenes and scenarios - have so far remained elusive. In an attempt to come closer to understanding the fundamental principles of cortical computation, here we present a functional, phenomenological model of the primate visual cortex. The core part of the model describes four hierarchical cortical areas with feedforward, lateral, and recurrent connections. The three main principles implemented in the model are information compression, unsupervised learning by prediction, and use of lateral and top-down context. We show that the model reproduces key aspects of the primate ventral stream of visual processing including Simple and Complex cells in V1, increasingly complicated feature encoding, and increased separability of object representations in higher cortical areas. The model learns representations of the visual environment that allow for accurate classification and state-of-the-art visual tracking performance on novel objects.

The hardware and software foundations laid in the first half of the 20th Century enabled the computing technologies that have transformed the world, but these foundations are now under siege. The current computing paradigm, which is the foundation of much of the current standards of living that we now enjoy, faces fundamental limitations that are evident from several perspectives. In terms of hardware, devices have become so small that we are struggling to eliminate the effects of thermodynamic fluctuations, which are unavoidable at the nanometer scale. In terms of software, our ability to imagine and program effective computational abstractions and implementations are clearly challenged in complex domains. In terms of systems, currently five percent of the power generated in the US is used to run computing systems - this astonishing figure is neither ecologically sustainable nor economically scalable. Economically, the cost of building next-generation semiconductor fabrication plants has soared past $10 billion. All of these difficulties - device scaling, software complexity, adaptability, energy consumption, and fabrication economics - indicate that the current computing paradigm has matured and that continued improvements along this path will be limited. If technological progress is to continue and corresponding social and economic benefits are to continue to accrue, computing must become much more capable, energy efficient, and affordable. We propose that progress in computing can continue under a united, physically grounded, computational paradigm centered on thermodynamics. Herein we propose a research agenda to extend these thermodynamic foundations into complex, non-equilibrium, self-organizing systems and apply them holistically to future computing systems that will harness nature's innate computational capacity. We call this type of computing \"Thermodynamic Computing\" or TC.

The electrical properties of superconducting $\\rm YBa\\sb2Cu\\sb3O\\sb x$ thin films are extremely sensitive to the presence of structural disorder, perhaps much more so than the elemental and alloy superconductors that were their predecessors. This dissertation presents a careful study of the relationship between several electrical transport properties and defect structures observed in $\\rm YBa\\sb2Cu\\sb3O\\sb x$ thin films. The motivation for this study is both the desire to identify important issues pertinent to technological application of these materials and to understand the physics of the superconductor. Technological development of these superconductors will require understanding and control of crystalline disorder in order to optimize the electrical properties pertinent to a given application. This work focuses on measurement and discussion of two important figures of merit in the application of superconductors, surface impedance and critical current density. Two general classes of defects have been found to have a large impact on these quantities, grain boundaries and atomic scale or point-like defects. Simple models of the effect of these defect structures clarify some important constraints for the development of a successful technology. The models also provide insight into the underlying physics. In general, the properties of $\\rm YBa\\sb2Cu\\sb3O\\sb x$ are partly consistent and partly inconsistent with conventional theories of superconductivity. This dissertation identifies some important, unresolved issues in understanding the nature of the superconducting state.