Search Results for "descent" - Page 2
Sort By:
Showing 70 open source projects for "descent"
View related business solutions-
Forever Free Full-Stack Observability | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
Stop Storing Third-Party Tokens in Your DatabaseRolling your own OAuth token storage can be a security liability. Token Vault securely stores access and refresh tokens from federated providers and handles exchange and renewal automatically. Connected accounts, refresh exchange, and privileged worker flows included.
-
1
Tensorflow and deep learning
A crash course in six episodes for software developers
...It is structured as a series of guided lessons that combine theoretical explanations, practical examples, and runnable code, allowing learners to build intuition while actively experimenting with models. The repository covers core neural network concepts such as weights, biases, activation functions, and gradient descent, as well as more advanced techniques like convolutional networks, recurrent networks, and reinforcement learning. It includes multiple hands-on projects, such as handwritten digit recognition, airplane detection in images, and text generation using recurrent neural networks, which demonstrate how different architectures solve real-world problems. -
2
SINGA
A distributed deep learning platform
...SINGA supports data parallel training across multiple GPUs (on a single node or across different nodes). SINGA supports various popular optimizers including stochastic gradient descent with momentum, Adam, RMSProp, and AdaGrad, etc. SINGA records the computation graph and applies the backward propagation automatically after forward propagation. The optimization of memory are implemented in the Device class. SINGA supports loading ONNX format models and saving models defined using SINGA APIs into ONNX format, which enables AI developers to use models across different libraries and tools. ... -
3
PyTorch Natural Language Processing
Basic Utilities for PyTorch Natural Language Processing (NLP)
...PyTorch-NLP comes with pre-trained embeddings, samplers, dataset loaders, metrics, neural network modules and text encoders. It’s open-source software, released under the BSD3 license. With your batch in hand, you can use PyTorch to develop and train your model using gradient descent. For example, check out this example code for training on the Stanford Natural Language Inference (SNLI) Corpus. Now you've setup your pipeline, you may want to ensure that some functions run deterministically. Wrap any code that's random, with fork_rng and you'll be good to go. Now that you've computed your vocabulary, you may want to make use of pre-trained word vectors to set your embeddings. -
4
GSMLBook
Recipes for basic machine learning algorithms using sklearn in jupyter
...Topics include linear, multilinear, polynomial, stepwise, lasso, ridge, and logistic regression; ROC curves and measures of binary classification; nonlinear regression (including an introduction to gradient descent); classification and regression trees; random forests; neural networks; probabilistic methods (KNN, naive Bayes', QDA, LDA); dimensionality reduction with PCA; support vector machines; and clustering with K-Means, hierarchical, and DBScan. Appendices provide a review of probability and linear algebra. While some mathematical foundation is provided, it is not essential for understanding the implementations. ... -
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
5
Coursera Machine Learning
Coursera Machine Learning By Prof. Andrew Ng
...It consolidates lecture references, programming tutorials, test cases, and supporting materials into one repository for easier review and practice. The project highlights fundamental machine learning concepts such as hypothesis functions, cost functions, gradient descent, bias-variance tradeoffs, and regression models. It also organizes week-by-week course schedules with links to exercises, lecture notes, and additional resources. Alongside the official coursework, the repository includes supplemental explanations, code snippets, and references to recommended textbooks and external materials. By gathering course-related resources into a single space, this project acts as a practical study companion for learners revisiting or supplementing the original course. -
6
Microsoft Cognitive Toolkit (CNTK)
Open-source toolkit for commercial-grade distributed deep learning
CNTK describes neural networks as a series of computational steps via a digraph which are a set of nodes or vertices that are connected with the edges directed between different vertexes. Create and combine models such as: -Feed-Forward DNNs -Convolutional neural networks -Recurrent neural networks -
7
sijinn
SImple Java Implementation of Neural Network
Alfa version - work in progress. Perseptron network structure. Can be saved in xml format. Training strategies: - Gradient Descent (Batch, Stochastic) - Genetic Breeding Training algorithms: - BPROP (back propagation) - QPROP (quick propagation) - RPROP (resilient propagation) - GENE (genetic neural) Demo: https://sijinn.herokuapp.com/ http://sijinn.appspot.com/network GitHub: https://github.com/surban1974/sijinn Maven <repositories> <repository> <id>neohort-mvn-repo</id> <url>https://github.com/surban1974/sijinn/raw/mvn-repo/</url> <snapshots> <enabled>true</enabled> <updatePolicy>always</updatePolicy> </snapshots> </repository> </repositories> <dependency> <groupId>com.github.surban1974.sijinn</groupId> <artifactId>sijinn-base</artifactId> <version>1.1.2-alfa</version> </dependency> -
8
Mocha.jl
Deep Learning framework for Julia
Mocha.jl is a deep learning framework for Julia, inspired by the C++ Caffe framework. It offers efficient implementations of gradient descent solvers and common neural network layers, supports optional unsupervised pre-training, and allows switching to a GPU backend for accelerated performance. The development of Mocha.jl happens in relative early days of Julia. Now that both Julia and the ecosystem has evolved significantly, and with some exciting new tech such as writing GPU kernels directly in Julia and general auto-differentiation supports, the Mocha codebase becomes excessively old and primitive. ... -
9
popt4jlib
Parallel Optimization Library for Java
...Implements a number of meta-heuristic algorithms for Non-Linear Programming, including Genetic Algorithms, Differential Evolution, Evolutionary Algorithms, Simulated Annealing, Particle Swarm Optimization, Firefly Algorithm, Monte-Carlo Search, Local Search algorithms, Gradient-Descent-based algorithms, as well as some well-known network flow and other graph algorithms. A fast parallel implementation of the network simplex method, and some full-fledged parallel/distributed MIP solvers will be added in the next version. In general, emphasis is given in improving the efficiency of the algorithms in shared-memory models via java threads, since multi-core machines are so wide-spread today. -
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
10
Descent OS
Debian-Based Mate Distribution
Descent OS is a Linux distribution designed around usability and resources. Descent OS utilizes the MATE Desktop Environment for functionality, and is prettied up and utilized for everyone's needs. We aim to provide a modern, clean, and quick desktop interface. Descent OS incorporates ease of use with the power that advanced users hunger, with emphasis on functionality and lightness. -
11
Cambridge Rocketry Simulator
Simulate high power rocket flights with splash down plots
This software allows you perform six degree of freedom simulations of High Power Rocket (HPR) and model rocket flights. Parachute descent is also simulated. 3D flight trajectories are produced as well as detailed tabular flight data. Running in Monte Carlo mode allows generates multiple possible flight paths and splash down plots, indicating the probability of landing in an area. Peer-reviewed publication in the Journal of Open Research Software (JORS) http://doi.org/10.5334/jors.137 "Cambridge Rocketry Simulator – A Stochastic Six-Degrees-of-Freedom Rocket Flight Simulator" -
12
CurvatureFilter
Curvature Filters are efficient solvers for Variational Models
...MC filter and TV filter are exactly the same as described in the paper. However, the GC filter is slightly modified. Please cite the following papers if you use a curvature filter in your work. Traditional solvers, such as gradient descent or Euler Lagrange Euqation, start at the total energy and use diffusion scheme to carry out the minimization. When the initial condition is the original image, the data fitting energy always increases while the regularization energy always reduces during the optimization. Thus, regularization energy must be the dominant part since the total energy has to decrease. ... -
13
Steepest-descent-like search algorithm
Heuristic search to find 21-variable PW type functions with NL>1047552
...Maitra) 1) The file "pw21_nlac.zip" contains the source code which computes the nonlinearity and absolute indicator of 21-variable PW type functions obtained from the 4 solutions in Table 1 of our paper (available at http://eprint.iacr.org/2015/1036). See comments in "pw21_nlac.cpp" in the zipped file for details. 2) Steepest-descent-like iterative search algorithm used in the same paper is implemented using the files in "sdl_algo.zip" which are briefly described as follows: "stp_ineq_pw21.cpp": Main file containing the source code (see comments therein for details). "ADK.txt": Contains the integer values corresp. to the vector space representations of nonzero elements in GF(2^{21}). ... -
14
# ASPI Kit - Adaptive Identification and Control Software This software is under development by the ASPICC group. Its purpose is to allow users to learn and experiment the use of Neural Networks (NN's) and related Computational Intelligence algorithms on their own data. Users can upload their own data and experiment with various algorithms of various setups to see how the algorithms performs on their data. Users can also investigate and familiarize themselves with the Python code of...
-
15
A satirical console-based political role-playing/strategy game in which you recruit a team of Elite Liberal radicals and try to save the United States from a descent into Arch-Conservatism. Gameplay based loosely on the classic 1983 RPG Oubliette.
-
16
Toolkit for processing genetic data. Currently supports (command-line): Half-IBD (Identity by descent) aka HIRs - between 2 or any number of files (in distances and cM); RAW2PED, PED2RAW conversions; regions of homozygousity and other converters.
-
17
JPOP is a pure java parallel optimization package based on the Optimization Java Package. It supports analytical gradients and Hessians for non-linear optimization. JPOP is based on uncmin in Fortran but employs java arrays and object oriented code.
-
18
diCal-IBD
diCal-IBD predicts identical by descent tracts using sequence data
diCal-IBD can be used for predicting identical by descent (IBD) tracts in sequence data. It provides means for calculating the accuracy of the prediction, if the true tracts are available, plotting of the predicted tracts, their TMRCA (time to the most recent common ancestor) and corresponding posterior probabilities, and identification of putative recent positive selection through investigation of average IBD sharing -
19
Human Speakable Programming Language
foundation of the General Intelligence Operating System
HSPL is Human Speakable Programming Language, allowing for communication between human-to-computer and human-to-human in the same language. This project has moved to http://sourceforge.net/p/spel We are currently working on human-to-computer programming-language with mostly English base vocabulary. Though once we have that, we plan to add support for other world Languages, including Chinese, Spanish, Russian, Arabic, Hindi, among others. Eventually HSPL shall be the... -
20
CURRENNT
CUDA-enabled machine learning library for recurrent neural networks
CURRENNT is a machine learning library for Recurrent Neural Networks (RNNs) which uses NVIDIA graphics cards to accelerate the computations. The library implements uni- and bidirectional Long Short-Term Memory (LSTM) architectures and supports deep networks as well as very large data sets that do not fit into main memory. -
21
BudgetedSVM
BudgetedSVM: A C++ Toolbox for Large-scale, Non-linear Classification
We present BudgetedSVM, a C++ toolbox containing highly optimized implementations of three recently proposed algorithms for scalable training of Support Vector Machine (SVM) approximators: Adaptive Multi-hyperplane Machines (AMM), Budgeted Stochastic Gradient Descent (BSGD), and Low-rank Linearization SVM (LLSVM). BudgetedSVM trains models with accuracy comparable to LibSVM in time comparable to LibLinear, as it allows solving highly non-linear classi fication problems with millions of high-dimensional examples within minutes on a regular personal computer. We provide command-line and Matlab interfaces to BudgetedSVM, efficient API for handling large-scale, high-dimensional data sets, as well as detailed documentation to help developers use and further extend the toolbox. -
22
sdEM
Stochastic Discriminative Expectation Maximization (sdEM)
Stochastic discriminative EM (sdEM) is an online-EM-type algorithm for discriminative training of probabilistic generative models belonging to the natural exponential family. In this work, we introduce and justify this algorithm as a stochastic natural gradient descent method, i.e. a method which accounts for the information geometry in the parameter space of the statistical model. We show how this learning algorithm can be used to train probabilistic generative models by minimizing different discriminative loss functions, such as the negative conditional log-likelihood and the Hinge loss. The resulting models trained by sdEM are always generative (i.e. they define a joint probability distribution) and, in consequence, allows to deal with missing data and latent variables in a principled way either when being learned or when making predictions. -
23
Soul is a recursive descent parser generator tool for Windows and Linux that comes with a parsing library.
-
24
...**Wide range of supported ML algorithms** All supervised learning algorithms supported by scikit-learn, as well as Artificial Neural Networks (ANNs) **Fast Learning and Evaluation** Thanks to scikit-learn and FANN, all supported ML algorithms are optimized and written in C/C++ language. **Built-in attack algorithms** Gradient Descent Attack **Extensible** Other attack algorithms can be easily added to the library. **Multi-processing** Do you want to further save time? The built-in attack algorithms can run concurrently on multiple processors. Last, but not least, AdversariaLib is **free software**, released under the GNU General Public License version 3!
-
25
NOTE: This project was moved to: https://github.com/eetorres The BPANNA is a flexible Back propagation neural network, which include the Conjugate Gradient and the Levenberg-Marquardt. You can change the number of inputs, number of layers, number of neurons per layer and outputs. It included an structure editor.
