Search Results for "learning"

Megatron-LM is a GPU-optimized deep learning framework from NVIDIA designed to train extremely large transformer-based language models efficiently at scale. The repository provides both a reference training implementation and Megatron Core, a composable library of high-performance building blocks for custom large-model pipelines. It supports advanced parallelism strategies including tensor, pipeline, data, expert, and context parallelism, enabling training across massive multi-GPU and multi-node clusters. ...

...This comprehensive guide covers a lot of essentials and is written in a clear and concise style, showing the result vs code. Plus, it's #opensource and freely available, creating a collaborative learning environment. In this book the I try to reveal how you can find necessary pieces of TeX code looking only at already done work. If you want to create high-quality documents with LaTeX, check out the LaTaX book on GitHub, and feel free to ask any questions you have.

Deep-Learning-for-Medical-Applications is a repository that compiles deep learning methods, code implementations, and examples applied to medical imaging and healthcare data. The project addresses domain-specific challenges like segmentation, classification, detection, and multimodal data (e.g. MRI, CT, X-ray) using state-of-the-art architectures (e.g.

...It also includes tools for managing and profiling large music collections and for checking audio for production errors. jMIR includes software for extracting features, applying machine learning algorithms, applying heuristic error error checkers, mining metadata and analyzing metadata.

Web site to translate text from Spanish to a regular Spanish called "espanes". This lenguage adaptation is very useful for learning Spanish because ia a simplified version with less verbal modes, accents enhanced, prefix, infix and suffix reduced....

This is a Java API binding of the IEEE LTSC LOM (Learning Object Metadata) specification. It defines an implementation neutral Java interface for the LOM, as well as providing a default implementation of that interface, and XML marshalling functionality

The National STEM Distributed Learning (NSDL) program is a national network dedicated to advancing STEM teaching and learning for all learners in both formal and informal settings.

...I wrote it over three years ago, and wrote it in quite a hurry when I did. If you compare this stuff with my GPE code, its like night and day. Well, hopefully somebody learning to work with OGRE or to program in C++, might find it useful

NetLingua creates free, quality instructional materials (textbooks, grammars etc.) for learning natural languages (Chinese, Spanish, Swahili, Latin, Manchu, Akkadian,...). Our sources are in utf-8 encoded LaTeX files, we release PDF e-books.

A front end (middleware) system for interacting with the ADL-R (Advanced Distributed Learning - Repository) metadata repository. Web-based service keeps track of the state of your repository and allows you several ways to update the ADL-R via SOAP calls.

This project contains a framework, built to be used in a Digital Game Design Undergraduate course. Such framework allow a better learning of object-oriented principles by first-grade students.

PALOMA Suite allows the referencing of learning resources using metadata according to the international IEEE LOM standard, and SCORM, CANCORE and Normetic application profiles. PALOMA Suite contains: PALOMA (Standard), PALOMAWeb and PALOMARepository.

KNN-WEKA provides a implementation of the K-nearest neighbour algorithm for Weka. Weka is a collection of machine learning algorithms for data mining tasks. For more information on Weka, see http://www.cs.waikato.ac.nz/ml/weka/.

An activity social module for Moodle Learning Environment. StructuredForum is based on three types of generic contributions, namely specification, elaboration and consensus.