2 Repos
Awesome GitHub RepositoriesManifold Regularization
Regularization techniques that enforce invariance along the tangent directions of the data manifold.
Distinct from Manifold Learning Guides: Existing candidates focus on 3D geometry tangents or general manifold learning, not the specific regularization of neural networks via manifold tangents.
Explore 2 awesome GitHub repositories matching artificial intelligence & ml · Manifold Regularization. Refine with filters or upvote what's useful.
Awesome Manifold Regularization GitHub Repositories
Finde die besten Repos mit KI.Wir suchen mit KI nach den am besten passenden Repositories.
- exacity/deeplearningbook-chinese
exacity/deeplearningbook-chinese
37,285Auf GitHub ansehenThis project is a comprehensive Chinese translation of a technical deep learning textbook, providing an educational resource on the theory and implementation of neural networks. It functions as a collaborative technical translation project designed to make complex academic AI literature accessible to non-English speakers. The project utilizes a community-driven translation model that integrates external suggestions and pull requests to refine linguistic accuracy and reduce bias. It employs standardized terminology mapping to ensure a uniform vocabulary throughout the translated content. To i
Explains how to regularize model outputs to be invariant to changes along the tangent directions of the data manifold.
TeX - microsoft/trellis.2
microsoft/TRELLIS.2
3,910Auf GitHub ansehenTRELLIS.2 is a generative image-to-3D system that creates high-resolution 3D assets with physically based rendering materials from 2D images. It utilizes a sparse voxel representation to handle complex topologies and internal structures without relying on iso-surface fields. The project features a structured latent space representation that maps geometry and texture attributes to maintain visual fidelity. It employs an optimization-free geometry reconstruction process to decode latent representations directly into voxel grids and includes a PBR texture generator for synthesizing base color, r
Employs representations for arbitrary 3D surfaces that bypass the constraints of closed manifolds.
Python
