20 results for “Compositional Pattern Producing Networks”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
Sublinearly structured DNNs achieve feature-learning and prediction consistency comparable to classical models
This paper characterizes the gap between neural network performance and their neural tangent kernel limit on compositional tasks, attributing it to a mismatch between kernel smoothness bias and target…
The paper introduces the Vector Network (VN), a novel recurrent architecture that replaces fixed weight matrices with reusable weight atoms, enabling superior compositional generalization by making st…
This paper explores the relationship between neural network architecture and computational ability, identifying local cycles as a key design principle.
The paper proposes a unified framework for designing efficient and expressive token mixing layers by separating the direct and recurrent influences of inputs, allowing for a principled trade-off betwe…
This paper studies a random compositional model for the growth of affine regions in deep piecewise-linear networks and proves the existence of a submultiplicative pressure for the number of affine pie…
This paper studies how modular architecture and representational dimensionality affect compositional continual learning in a sequential A-B-A paradigm.
Introduces Expanding Generative Flows (EFlows) and Expanding Flow Maps (EFMs) for generating outputs of varying sizes in continuous and discrete state spaces.
This paper studies the structural expressivity and parameterized complexity of counting homomorphisms from small temporal patterns to large temporal graphs, proving a temporal Lovász-style theorem, in…
Tieyao Zhang, Yuke Liu, Jiaxing Yu, Xinda Wu +2 more
This paper proposes RPPNet, a two-stage deep learning architecture for music generation with variable structural boundaries, which automatically derives grouping of Rhythm-Pitch Primitive sequences fr…
This book provides a compact, derivation-oriented mathematical primer that connects major families of generative AI models, showing their underlying structural relationships.
The paper introduces Compositional Semantic Fingerprinting (CSF), a black-box method that allows IP owners to attribute fine-tuned text-to-image models to their protected lineages using only query acc…
This paper proposes a new definition of source in source tracing as a compositional tuple of Architecture, Training Data, and other training factors, and introduces a framework using Structured Orthon…
Yen-Tung Yeh, Chung-Jui Chan, Yun-Ning, Hung +1 more
This paper proposes a sequential stem blending approach for automatic music mixing, enabling processing of an arbitrary number of input tracks.
This paper challenges the claim that neural networks have met the challenge of systematicity in language and thought as proposed by Fodor and Pylyshyn, demonstrating limitations in a recent neural net…