131 research outputs found
The Quantum Path Kernel: A Generalized Neural Tangent Kernel for Deep Quantum Machine Learning
No full textBuilding a quantum analog of classical deep neural networks represents a fundamental challenge in quantum computing. A key issue is how to address the inherent nonlinearity of classical deep learning, a problem in the quantum domain due to the fact that the composition of an arbitrary number of quantum gates, consisting of a series of sequential unitary transformations, is intrinsically linear. This problem has been variously approached in literature, principally via the introduction of measurements between layers of unitary transformations. In this article, we introduce the quantum path kernel (QPK), a formulation of quantum machine learning capable of replicating those aspects of deep machine learning typically associated with superior generalization performance in the classical domain, specifically, hierarchical feature learning. Our approach generalizes the notion of quantum neural tangent kernel, which has been used to study the dynamics of classical and quantum machine learning models. The QPK exploits the parameter trajectory, i.e., the curve delineated by model parameters as they evolve during training, enabling the representation of differential layerwise convergence behaviors, or the formation of hierarchical parametric dependencies, in terms of their manifestation in the gradient space of the predictor function. We evaluate our approach with respect to variants of the classification of Gaussian xormixtures: an artificial but emblematic problem that intrinsically requires multilevel learning in order to achieve optimal class separation.Building a quantum analog of classical deep neural networks represents a fundamental challenge in quantum computing. A key issue is how to address the inherent non-linearity of classical deep learning, a problem in the quantum domain due to the fact that the composition of an arbitrary number of quantum gates, consisting of a series of sequential unitary transformations, is intrinsically linear. This problem has been variously approached in the literature, principally via the introduction of measurements between layers of unitary transformations. In this paper, we introduce the Quantum Path Kernel, a formulation of quantum machine learning capable of replicating those aspects of deep machine learning typically associated with superior generalization performance in the classical domain, specifically, hierarchical feature learning. Our approach generalizes the notion of Quantum Neural Tangent Kernel, which has been used to study the dynamics of classical and quantum machine learning models. The Quantum Path Kernel exploits the parameter trajectory, i.e. the curve delineated by model parameters as they evolve during training, enabling the representation of differential layer-wise convergence behaviors, or the formation of hierarchical parametric dependencies, in terms of their manifestation in the gradient space of the predictor function. We evaluate our approach with respect to variants of the classification of Gaussian XOR mixtures - an artificial but emblematic problem that intrinsically requires multilevel learning in order to achieve optimal class separation
Hamming Distance Kernelisation via Topological Quantum Computation
No full textWe present a novel approach to computing Hamming distance and its kernelisation within Topological Quantum Computation. This approach is based on an encoding of two binary strings into a topological Hilbert space, whose inner product yields a natural Hamming distance kernel on the two strings. Kernelisation forges a link with the field of Machine Learning, particularly in relation to binary classifiers such as the Support Vector Machine (SVM). This makes our approach of potential interest to the quantum machine learning community
Multi-disciplinary Trends in Artificial Intelligence: 16th International Conference, MIWAI 2023, Hyderabad, India, July 21–22, 2023, Proceedings
No full textThe 47 full papers and 24 short papers included in this book were carefully reviewed and selected from 245 submissions. These articles cater to the most contemporary and happening topics in the fields of AI that range from Intelligent Recommendation Systems, Game Theory, Computer Vision, Reinforcement Learning, Social Networks, and Generative AI to Conversational and Large Language Models.
They are organized into four areas of research: Theoretical contributions, Cognitive Computing models, Computational Intelligence based algorithms, and AI Applications
Morphologically Debiased Classifier Fusion: A Tomography-Theoretic Approach
No full textWe set out in this review article to construct a generalized theory of classi er combination for classi ers that, at least in the theory's initial form, act within noncoincident feature-spaces. Doing so involves the postulation of an equivalence between the various strategies for classi er combination and the tomographic reconstruction of the joint pattern-space probability density function, where the classi ers themselves are interpreted as extremely bandwidth limited Radon transform data. This analogue will immediately suggest techniques for improving the process, as well as de ning the optimal performance to be gained by such combinatorial approaches with respect to arbitrary joint pattern-space PDF morphologies. Furthermore, this methodology of optimality naturally will also encompass the feature selection process to present a uni ed perspective on the various di ering aspects of classi er combination. A practical implementation of the methodology is also given, along with a series of tests to establish its performance in relation to both model and real-word classi cation scenarios
Emergent Intentionality in Perception-Action Subsumption Hierarchies
No full textA cognitively autonomous artificial agent may be defined as one able to modify both its external world-model and the framework by which it represents the world, requiring two simultaneous optimization objectives. This presents deep epistemological issues centered on the question of how a framework for representation (as opposed to the entities it represents) may be objectively validated. In this article, formalizing previous work in this field, it is argued that subsumptive perception-action learning has the capacity to resolve these issues by (a) building the perceptual hierarchy from the bottom up so as to ground all proposed representations and (b) maintaining a bijective coupling between proposed percepts and projected action possibilities to ensure empirical falsifiability of these grounded representations. In doing so, we will show that such subsumptive perception-action learners intrinsically incorporate a model for how intentionality emerges from randomized exploratory activity in the form of “motor babbling.” Moreover, such a model of intentionality also naturally translates into a model for human–computer interfacing that makes minimal assumptions as to cognitive states
Representational fluidity in embodied (artificial) cognition
No full textTheories of embodied cognition agree that the body plays some role in human cognition, but disagree on the precise nature of this role. While it is (together with the environment) fundamentally engrained in the so-called 4E (or multi-E) cognition stance, there also exists interpretations wherein the body is merely an input/output interface for cognitive processes that are entirely computational. In the present paper, we show that even if one takes such a strong computationalist position, the role of the body must be more than an interface to the world. To achieve human cognition, the computational mechanisms of a cognitive agent must be capable not only of appropriate reasoning over a given set of symbolic representations; they must in addition be capable of updating the representational framework itself (leading to the titular representational fluidity). We demonstrate this by considering the necessary properties that an artificial agent with these abilities need to possess. The core of the argument is that these updates must be falsifiable in the Popperian sense while simultaneously directing representational shifts in a direction that benefits the agent. We show that this is achieved by the progressive, bottom-up symbolic abstraction of low-level sensorimotor connections followed by top-down instantiation of testable perception-action hypotheses. We then discuss the fundamental limits of this representational updating capacity, concluding that only fully embodied learners exhibiting such a priori perception-action linkages are able to sufficiently ground spontaneously-generated symbolic representations and exhibit the full range of human cognitive capabilities. The present paper therefore has consequences both for the theoretical understanding of human cognition, and for the design of autonomous artificial agents
Trained Eyes: Experience Promotes Adaptive Gaze Control in Dynamic and Uncertain Visual Environments
No full textThis is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.This work was supported by grants from Engineering and Physical Sciences Research Council (EP/F069626/1)
A paper on paper : value systems and the Australian pulp and paper industry
No full textThis thesis was scanned from the print manuscript for digital preservation and is copyright the author.
Researchers can access this thesis by asking their local university, institution or public library to
make a request on their behalf. Monash staff and postgraduate students can use the link in the References field
- …
