arXiv research

New algorithms compute Volterra signature efficiently for time series analysis.

We investigate some relations concerning the first and the second Beltrami operators corresponding to the fundamental forms I, II, III of a surface in the three-dimensional Euclidean space and we study surfaces which are of finite type in the sense of B.-Y. Chen with respect to the fundamental forms II and III.

In this paper, we study ruled surfaces and quadrics in the 3-dimensional Euclidean space which are of finite $III$-type, that is, they are of finite type, in the sense of B.-Y. Chen, with respect to the third fundamental form. We show that helicoids and spheres are the only ruled and quadric surfaces of finite $III$-ty…

We give necessary and sufficient conditions for the real distributions defined by a metallic pseudo-Riemannian structure to be integrable and geodesically invariant, in terms of associated tensor fields to the metallic structures and of adapted connections. In the integrable case, we prove a Chen-type inequality for th…

In [6] we proved Chen's inequality regarded as a problem of constrained maximum. In this paper we introduce a Riemannian invariant obtained from Chen's invariant, replacing the sectional curvature by the Ricci curvature of k-order. This invariant can be estimated, in the case of submanifolds M in space forms $\widetild…

Study properties of surfaces with nonvanishing third fundamental form.

Study geometric inequalities for CR-submanifolds using curvature invariants.

New comparison theorem for submanifolds with geometric inequalities.

Establish generalized Chen inequalities for Riemannian submersions and Riemannian maps with applications.

We classify Hopf hypersurfaces of non-flat complex space forms CP^m(4) and CH^m(-4), denoted jointly by CQ^m(4c), that are of 2-type in the sense of B. Y. Chen, via the embedding into a suitable (pseudo) Euclidean space of Hermitian matrices by projection operators. This complements and extends earlier classifications …

The study classifies hypersurfaces in quaternionic space forms with constant principal curvatures.

DeepCAM learns convolutional dictionaries for image processing.

Introduces Finslerian convolution metrics and their properties.

Spectral graph convolutional neural networks (CNNs) require approximation to the convolution to alleviate the computational complexity, resulting in performance loss. This paper proposes the topology adaptive graph convolutional network (TAGCN), a novel graph convolutional network defined in the vertex domain. We provi…

Generative flows are attractive because they admit exact likelihood optimization and efficient image synthesis. Recently, Kingma & Dhariwal (2018) demonstrated with Glow that generative flows are capable of generating high quality images. We generalize the 1 x 1 convolutions proposed in Glow to invertible d x d convolu…

VC dimensions of group CNNs are infinite for certain kernels and groups.

We introduce a guide to help deep learning practitioners understand and manipulate convolutional neural network architectures. The guide clarifies the relationship between various properties (input shape, kernel shape, zero padding, strides and output shape) of convolutional, pooling and transposed convolutional layers…

Enhances group convolutional networks with attention to learn meaningful relationships.

Convolution Neural Network (CNN) has gained tremendous success in computer vision tasks with its outstanding ability to capture the local latent features. Recently, there has been an increasing interest in extending convolution operations to the non-Euclidean geometry. Although various types of convolution operations h…

We introduce Group equivariant Convolutional Neural Networks (G-CNNs), a natural generalization of convolutional neural networks that reduces sample complexity by exploiting symmetries. G-CNNs use G-convolutions, a new type of layer that enjoys a substantially higher degree of weight sharing than regular convolution la…

In recent times, the use of separable convolutions in deep convolutional neural network architectures has been explored. Several researchers, most notably (Chollet, 2016) and (Ghosh, 2017) have used separable convolutions in their deep architectures and have demonstrated state of the art or close to state of the art pe…

Proves DCNNs with expansive convolution are strongly universally consistent.

New framework for manifold convolutions using toric embeddings.

Functor connects Lie groupoid algebras to bornological structures.

Convolution has been playing a prominent role in various applications in science and engineering for many years. It is the most important operation in convolutional neural networks. There has been a recent growth of interests of research in generalizing convolutions on curved domains such as manifolds and graphs. Howev…

Convolutional Neural Networks, as most artificial neural networks, are commonly viewed as methods different in essence from kernel-based methods. We provide a systematic translation of Convolutional Neural Networks (ConvNets) into their kernel-based counterparts, Convolutional Kernel Networks (CKNs), and demonstrate th…

New method enforces orthogonality in convolutional layers for improved robustness.

New method improves grouped convolutions on edge devices.

GCNs improve regression tasks by aggregating neighbor signals.

Convolution and pooling improve kernel methods in image classification.

Convolutional networks outperform fully-connected ones in certain tasks.

Proposes a fixed smooth convolutional layer to reduce checkerboard artifacts in CNNs.

This work proposes hyperbolic deep convolutional neural networks for better pattern recognition.

New linear flows using exponential of linear transformations improve generative models.

Convolutional neural networks (CNNs) have achieved breakthrough performances in a wide range of applications including image classification, semantic segmentation, and object detection. Previous research on characterizing the generalization ability of neural networks mostly focuses on fully connected neural networks (F…

We describe convolutional networks using harmonic functions.

Proposes a new convolutional neural network for non-grid data.

New mechanism discovered for feature learning in CNNs.

Coordinate-independent convolutions on manifolds avoid reference frame ambiguity.

Recently, many researchers have been focusing on the definition of neural networks for graphs. The basic component for many of these approaches remains the graph convolution idea proposed almost a decade ago. In this paper, we extend this basic component, following an intuition derived from the well-known convolutional…

Yes, they do. This paper provides the first empirical demonstration that deep convolutional models really need to be both deep and convolutional, even when trained with methods such as distillation that allow small or shallow models of high accuracy to be trained. Although previous research showed that shallow feed-for…

Unified theory for adaptive image convolutions using metric perspectives.

Ensemble learning is a method of combining multiple trained models to improve model accuracy. We propose the usage of such methods, specifically ensemble average, inside Convolutional Neural Network (CNN) architectures by replacing the single convolutional layers with Inner Average Ensembles (IEA) of multiple convoluti…

Simplifies convolutions using tensor networks and einsum for efficient second-order methods.

TaLK Convolutions improve sequence modeling efficiency.

Introduces new algebraic structures for relational groupoids and proves a reduction theorem.

The paper proposes an ensemble of convolution-based methods for fault detection in gearboxes.

Study convolution of invariant valuations on Lie groups.