Search Results for "meta"

* Fast C++ library for linear algebra (matrix maths) and scientific computing * Easy to use functions and syntax, deliberately similar to Matlab / Octave * Uses template meta-programming techniques to increase efficiency * Provides user-friendly wrappers for OpenBLAS, Intel MKL, LAPACK, ATLAS, ARPACK, SuperLU and FFTW libraries * Useful for machine learning, pattern recognition, signal processing, bioinformatics, statistics, finance, etc. * Downloads: https://arma.sourceforge.net/download.html * Documentation: https://arma.sourceforge.net/docs.html * Bug reports: https://arma.sourceforge.net/faq.html * Git repo: https://gitlab.com/armadillo-lib/armadillo-code

The supervised-reptile repository contains code associated with the paper “On First-Order Meta-Learning Algorithms”, which introduces Reptile, a meta-learning algorithm for learning model parameter initializations that adapt quickly to new tasks. The implementation here is aimed at supervised few-shot learning settings (e.g. Omniglot, Mini-ImageNet), not reinforcement learning, and includes scripts to run training and evaluation for few-shot classification.

jsprit is a java based, open-source toolkit for solving rich Traveling Salesman Problems(TSP) and Vehicle Routing Problems(VRP). It is lightweight, flexible and easy-to-use, and based on a single all-purpose meta-heuristic. Setting up the problem, defining additional constraints, modifying the algorithms and visualizing the discovered solutions is as easy and handy as reading classical VRP instances to benchmark your algorithm. It is fit for change and extension due to its modular design and a comprehensive set of unit and integration tests. ...

...The dataset provides both an image representation of each character and the time-ordered stroke coordinates ([x, y, t]) for each instance. Includes stroke data (time-sequenced coordinates) per sample. The repository is intended as a benchmark dataset in few-shot / meta-learning research, not as a plug-and-play detection or classification engine. Pre-split “background” and “evaluation” alphabets for standard benchmarking.

Machine learning models for edge devices need to have a small footprint in terms of storage, prediction latency, and energy. One instance of where such models are desirable is resource-scarce devices and sensors in the Internet of Things (IoT) setting. Making real-time predictions locally on IoT devices without connecting to the cloud requires models that fit in a few kilobytes.These algorithms can train models for classical supervised learning problems with memory requirements that are...

...The benchmarks that are included comprise ZDT, DTLZ, WFG, and the knapsack problem. The goal of Opt4J is to simplify the evolutionary optimization of user-defined problems as well as the implementation of arbitrary meta-heuristic optimization algorithms. For this purpose, Opt4J relies on a module-based implementation and offers a graphical user interface for the configuration as well as a visualization of the optimization process.

The following code is a parallel kNN implementation that uses GPUs for the high dimensional data in text classification. You can use it to classify documents using kNN or to generate meta-features based on the distances between a query document and its k nearest neigbors

Booleans all meshes on the screen. Plus: A fractal generator and attractor generator with a delicious SEARCH function ;) <meta name="google-site-verification" content="cULQewNGfx-aXCQR9fTJZ1Z7DXbLA5GjqjvAfF_oH5I" />

Search Agents - a framework for collaboration of meta-heuristic agents

TypeRecognizer is C++ class which enables the developer to recognize data types in compile-time

Common Java data structure library used by multiple projects. See http://verdantium.blogspot.com/

MAIF is developed in Java 5 (especially Generics) and aims at building AI algorithms, by concentrating onto the mapping of real-world problems, while abstracting from their inner working. It can be extended with new algorithms and problem representations.

MultiBoost is a C++ implementation of the multi-class AdaBoost algorithm. AdaBoost is a powerful meta-learning algorithm commonly used in machine learning. The code is well documented and easy to extend, especially for adding new weak learners.

A java framework for developing meta-heuristics that supports the use of grids environments. The meta-heuristics planned to be realeased are GAs, VNS and NNs. The grid middleware that will be firstly explored is the OurGrid solution.

This projects implements various optimization heuristics and meta-heuristics (such as local search, VND, GRASP, Simulated Annealing, and more still to come) finding solutions on the post enrolment course timetabling problem.