TL;DR
A novel approach to CNN architecture optimization is proposed by leveraging mathematical series—such as arithmetic, geometric, or harmonic progressions—to define structured, scalable, and interpretable layer configurations, offering a lightweight, reproducible framework for CNN configuration that can be adapted across diverse image analysis tasks.
The demand for more accurate Convolutional Neural Networks (CNNs) has led to increasingly deep and computationally expensive models. These architectures face limiting deployment and resource constraints when implemented. Static CNN models treat all input samples with identical computational density. These models are in...
A novel adaptive fusion framework that adaptively combines CNN and Transformer features through learnable gating, attention-based feature integration, and explainable-AI methods is developed, intended to improve both computational efficiency and model interpretability.
It is demonstrated that hyperparameter optimization dynamics depend heavily on dataset complexity, where computational efficiency is the primary differentiator for simpler classification tasks, but optimization architecture selection becomes critical for navigating challenging medical imaging applications.
Dynamic convolution enhances convolutional neural networks (CNNs) by adapting kernels to input content, but it expresses the effective kernel as a linear mixture of a small number of basis kernels, which limits expressivity and complicates optimization as the mixture size grows. In this work, we revisit dynamic convolu...
A Quantum-Enhanced Convolutional Neural Network model is developed, which incorporates traditional convolution-based feature extraction, Quantum Feature Encoding, and quantum processing and applies a quantum encoding mechanism to map classical features to quantum states for alternative feature representations and class...
This paper forms CNNs into a general index model with matrix-valued input, where convolution filters can be viewed as index vectors and proposes a novel singular value decomposition (SVD) based approach to accurately learn the convolution filters based on a generalized version of the first-order Stein's formula.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
