Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 13 of 13 for “"Vector Symbolic Architectures"”.

  1. In-memory Vector Symbolic Architectures

    … decade thanks primarily to deep neural network architectures and specialized hardware that support training the models within a reasonable time. However, since then a trend has emerged where, for solving increasingly difficult cognitive tasks, the model complexity in terms of the number of …

    ethz Repository record for In-memory Vector Symbolic Architectures (opens in a new tab)

  2. Exploring Symmetry and Representation in Vector Symbolic Architectures

    … this thesis, I explore and extend the methods of Vector Symbolic Architectures (VSAs), with a particular focus on Holographic Reduced Representations (HRRs) and group VSAs. Through a consideration of abstract groups and linear representation theory, I provide detailed analyses of these systems to …

    carleton Repository record for Exploring Symmetry and Representation in Vector Symbolic Architectures (opens in a new tab)

  3. Teach a robot to assemble a bolt to a nut with a handful of demonstrations

    … framework is first proposed, in which high-level symbolic action planning is performed using Vector Symbolic Architectures (VSA), and low-level 6D gripper trajectories are modeled using Task-parameterized Probabilistic Movement Primitives (TP-ProMPs). This approach enables both interpretable …

    waterloo Repository record for Teach a robot to assemble a bolt to a nut with a handful of demonstrations (opens in a new tab)

  4. Visual Imagery & Subjective Experiences: A Computational Perspective

    … bringing quality space models into the world of vector symbolic architectures is also presented, as is a novel approach to phenomenal consciousness. Finally, this thesis lays out what is (arguably) the minimum neural infrastructure needed to instantiate this alternative view of visual mental …

    carleton Repository record for Visual Imagery & Subjective Experiences: A Computational Perspective (opens in a new tab)

  5. Categories as a Foundation for both Learning and Reasoning

    … to machine learning. The first topic discusses Vector Symbolic Architectures (VSAs). I present the first attempt at formalising VSAs with category theory. VSAs are built to perform symbolic reasoning in high-dimensional vector spaces. I present a brief literature survey demonstrating that the …

    waterloo Repository record for Categories as a Foundation for both Learning and Reasoning (opens in a new tab)

  6. STRUCTURE ASSEMBLY IN KNOWLEDGE BASE REPRESENTATION

    … connectionist models in the tradition of Vector Symbolic Architectures (VSAs) provide a framework by which neural network models can integrate Fodor and Pylyshyn's insights, as well as the corresponding architectural commitments of cognitive theory. Other processes, based in Harmony …

    jhu Repository record for STRUCTURE ASSEMBLY IN KNOWLEDGE BASE REPRESENTATION (opens in a new tab)

  7. From Text to Neural Embeddings: Structuring Conceptual Knowledge in Large Language Models

    … thesis investigates the semantics encoded in the vector space of LLMs from a different perspective by addressing research questions related to the output-oriented interpretability of the semantic concepts represented within LLMs. It introduces a new probing paradigm, combining ideas from neural …

    trento Repository record for From Text to Neural Embeddings: Structuring Conceptual Knowledge in Large Language Models (opens in a new tab)

  8. A Defense of Pure Connectionism

    … principle—that proximal representations in a vector space have similar semantic values—is the key to a successful connectionist account of the systematicity and productivity of thought, language, and other core cognitive phenomena. My work here differs from preceding work in philosophy in …

    cuny-grad Repository record for A Defense of Pure Connectionism (opens in a new tab)

  9. Synapses and Routers for Neuromorphic Architectures Based on Emerging Memories

    … the semiconductor memory hierarchy and computing architectures. This thesis explores a hybrid memristive-CMOS approach that leverages NVMs to co-locate memory and computation, while also extending their functionality to neural communication through novel routing schemes. By incorporating …

    zurich

  10. Neurosymbolic Representation Learning with Holographic Reduced Representations

    … neural networks (DNNs) with explicit rule-based symbolic methods, a combination which is often known as a neurosymbolic AI system. Neurosymbolic methods can provide DNNs with the missing tools they need to symbolically represent and manipulate ideas, potentially enabling more rigorous reasoning …

    vt Repository record for Neurosymbolic Representation Learning with Holographic Reduced Representations (opens in a new tab)

  11. Associative Memory for Hyperdimensional Spatial Representations with Geodesic Flow Matching

    … the interior of the hypersphere, destroying the vector magnitude and phase relationships required for accurate decoding. By constraining transport dynamics to the intrinsic Riemannian geometry of the hypersphere, the proposed model preserves this structure even under severe corruption. The …

    waterloo Repository record for Associative Memory for Hyperdimensional Spatial Representations with Geodesic Flow Matching (opens in a new tab)