The hyperbolic Res-MLP (HR-MLP), an architecture extending the attention-free MLP to a non-Euclidean space and enabling direct hyperbolic operations with fewer parameters, facilitating faster training and superior performance compared to Euclidean counterparts is introduced.
We present hyperbolix, an open-source library for hyperbolic deep learning in JAX, built on Flax NNX. To our knowledge, it is the first comprehensive, general-purpose hyperbolic deep learning library in JAX. It includes six manifolds with a common interface: Euclidean space, the Poincar\'e ball, the hyperboloid, the $\...
Timo Klein, Thomas Lang, Yllka Velaj et al.· 0 citations
We investigate a general-purpose layer for deep learning that, instead of compressing arbitrary-size training data into fixed-size weight matrices, stores a new pair of key-value representations for every data point during training, and retrieves and recombines these representations through an attention mechanism at in...
Maximilian Schlegel, Rajai Nasser, Seijin Kobayashi et al.· 0 citations
Implicit Neural Representation (INR) leverages neural networks to represent discrete signals such as images as continuous ones, where the network weights serve as a compact form of the signal itself. Most existing INR methods adopt Multi-Layer Perceptrons (MLPs) as their backbone. Since these models render each pixel i...
Jing-Lei Shi, Xin-Ran Chang, Jiao Cui et al.· 0 citations
Recently, deep neural networks on manifold-valued representations have garnered significant attention across various machine learning applications. One recent focus is the generalization of Euclidean fully connected (FC) and convolutional layers to non-Euclidean geometries. However, previous approaches typically focus...
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.
Sarab Almuhaideb, Ahmad Raza Khan· Applied Sciences· 0 citations
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.
Guang Yang, Wei Shi, Yuan Cao et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
