awesome-repositories.com
Blog
MCP
awesome-repositories.com

Entdecke die besten Open-Source-Repositories mit KI-gestützter Suche.

EntdeckenKuratierte SuchenOpen-Source-AlternativenSelf-hosted SoftwareBlogSitemap
ProjektMCP-ServerÜber unsRanking-MethodikPresse
RechtlichesDatenschutzAGB
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

9 Repos

Awesome GitHub RepositoriesCost Functions

Mathematical objectives used to measure the discrepancy between predicted and actual values in machine learning.

Distinct from Objective Function Execution: Existing candidates refer to financial cost estimation or general objective function execution, not ML cost functions

Explore 9 awesome GitHub repositories matching artificial intelligence & ml · Cost Functions. Refine with filters or upvote what's useful.

Awesome Cost Functions GitHub Repositories

Finde die besten Repos mit KI.Wir suchen mit KI nach den am besten passenden Repositories.
  • exacity/deeplearningbook-chineseAvatar von exacity

    exacity/deeplearningbook-chinese

    37,285Auf GitHub ansehen↗

    This 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

    Provides guidance on specifying mathematical objectives to measure discrepancy between predictions and actual values.

    TeX
    Auf GitHub ansehen↗37,285
  • rasbt/python-machine-learning-bookAvatar von rasbt

    rasbt/python-machine-learning-book

    12,614Auf GitHub ansehen↗

    This project is an educational resource providing practical code examples and implementations of machine learning algorithms using the Python language. It serves as a guide for constructing predictive pipelines, clustering models, and dimensionality reduction within the Scikit-Learn ecosystem. The repository includes comprehensive demonstrations for supervised and unsupervised learning, as well as detailed examples for implementing neural networks and deep architectures. It also provides practical guidance on exporting model parameters to JSON and wrapping trained models in web APIs for produ

    Implements mathematical objectives to measure and minimize the discrepancy between predicted and actual values.

    Jupyter Notebook
    Auf GitHub ansehen↗12,614
  • morvanzhou/reinforcement-learning-with-tensorflowAvatar von MorvanZhou

    MorvanZhou/Reinforcement-learning-with-tensorflow

    9,464Auf GitHub ansehen↗

    This project is an educational repository of reinforcement learning agents and tutorials implemented using TensorFlow. It provides a practical codebase for both model-free and model-based learning agents, designed to demonstrate how AI agents learn through trial and error. The collection features detailed implementations of various algorithmic approaches, including Deep Q-Networks and Policy Gradient methods. It specifically covers Actor-Critic architectures for continuous and discrete action spaces, alongside Proximal Policy Optimization and Deep Deterministic Policy Gradients. The framewor

    Implements mathematical cost functions to monitor network convergence over the course of training steps.

    Pythona3cactor-criticasynchronous-advantage-actor-critic
    Auf GitHub ansehen↗9,464
  • vowpalwabbit/vowpal_wabbitAvatar von VowpalWabbit

    VowpalWabbit/vowpal_wabbit

    8,683Auf GitHub ansehen↗

    Vowpal Wabbit is an open-source machine learning system designed for online learning, where models update incrementally from streaming data without requiring full retraining. It provides a reduction-based learning framework that composes complex tasks from simpler algorithms, and includes a feature hashing trick that maps unbounded feature names into a fixed-size vector space to keep memory usage constant regardless of dataset size. The system supports distributed training across a cluster using an allreduce protocol for synchronized updates, and offers an active learning query strategy that s

    Trains models that minimize misclassification cost by learning from examples with per-class cost labels.

    C++active-learningc-plus-pluscontextual-bandits
    Auf GitHub ansehen↗8,683
  • hunkim/deeplearningzerotoallAvatar von hunkim

    hunkim/DeepLearningZeroToAll

    4,494Auf GitHub ansehen↗

    DeepLearningZeroToAll ist eine umfassende Bildungsressource und Implementierungssammlung mit Fokus auf Deep Learning und Machine Learning. Sie bietet einen strukturierten Lernpfad unter Verwendung von TensorFlow, um von grundlegenden linearen Modellen zu komplexen neuronalen Netzwerkarchitekturen zu gelangen. Das Projekt zeichnet sich durch seine praktischen Implementierungen verschiedener Netzwerktypen aus, darunter mehrschichtige Perzeptrone für Logikprobleme, Convolutional Neural Networks für räumliche Daten und Bilderkennung sowie Recurrent Neural Networks mit LSTM-Zellen für Zeitreihenprognosen und Zeichenfolgenvorhersagen. Es enthält zudem detaillierte Demonstrationen zur Modellregularisierung durch Batch-Normalisierung und Dropout-Techniken. Das Repository deckt ein breites Spektrum an Funktionen ab, einschließlich überwachtem Machine Learning mit linearer und logistischer Regression, Data Engineering für Tensor-Manipulation und Skalierung sowie Modelloptimierung durch Gradient Descent und manuelle Backpropagation-Berechnungen. Es enthält zudem Tools für die Modellevaluierung, Persistenz von Gewichten und Trainings-Observability durch Kostenfunktionsvisualisierung und Metrik-Logging. Die Inhalte werden über eine Reihe von Jupyter Notebooks vermittelt.

    Implements mathematical cost functions to measure prediction error for minimization via gradient descent.

    Jupyter Notebookkeraslabmxnet
    Auf GitHub ansehen↗4,494
  • ceres-solver/ceres-solverAvatar von ceres-solver

    ceres-solver/ceres-solver

    4,499Auf GitHub ansehen↗

    Ceres Solver ist eine C++-Bibliothek für numerische Optimierung, spezialisiert auf nichtlineare kleinste Quadrate und unbeschränkte Optimierungsprobleme. Sie dient als Framework für automatische Differenzierung und robuste Kurvenanpassung und bietet Tools zur Lösung mathematischer Modelle im großen Maßstab. Die Bibliothek zeichnet sich durch ihre Bundle-Adjustment-Funktionen aus, die spärliche Matrixstrukturen nutzen, um 3D-Szenenpunkte und Kameraparameter zu verfeinern. Sie verwendet dual-zahlbasierte automatische Differenzierung, um Ableitungen von Kostenfunktionen zu berechnen, wodurch die Notwendigkeit für manuelle Jacobian-Ableitung entfällt. Das Projekt deckt ein breites Spektrum an Optimierungsfunktionen ab, einschließlich Mannigfaltigkeits-Constraints für nicht-euklidische Räume, robuste Verlustfunktionen zur Minderung von Ausreißern sowie die Lösung dichter und spärlicher linearer Systeme. Es bietet zudem Dienstprogramme für die Konvertierung von Rotationsdarstellungen, tabellarische Dateninterpolation und Parameter-Kovarianzschätzung. Build-Konfigurationen sind für Android- und iOS-Ziele verfügbar, um die Optimierung mobiler Hardware zu unterstützen.

    Computes residuals and Jacobian matrices for terms in an objective function using multiple differentiation schemes.

    C++
    Auf GitHub ansehen↗4,499
  • zhm-real/motionplanningAvatar von zhm-real

    zhm-real/MotionPlanning

    2,702Auf GitHub ansehen↗

    MotionPlanning is a software library designed for autonomous navigation, providing a comprehensive suite of tools for path planning, trajectory generation, and vehicle control. It enables the calculation of collision-free routes and dynamic movement paths for autonomous vehicles operating in complex, changing environments. The project distinguishes itself by integrating hierarchical motion decomposition, which separates high-level route planning from low-level trajectory generation to manage computational complexity. It employs kinematic bicycle modeling and trailer dynamics simulation to ens

    Provides cost-function-based optimization to evaluate and select optimal movement paths for autonomous vehicles.

    Pythonautonomous-vehiclesfrenet-framesfront-wheel-feedback
    Auf GitHub ansehen↗2,702
  • pythonot/potAvatar von PythonOT

    PythonOT/POT

    2,751Auf GitHub ansehen↗

    POT is an optimal transport library providing a collection of solvers for computing Wasserstein, Gromov-Wasserstein, and Fused Gromov-Wasserstein distances between probability distributions. It functions as a differentiable tensor framework that integrates with various tensor libraries to enable automatic differentiation and GPU acceleration. The project is distinguished by its ability to align data distributions across different metric spaces by comparing internal relational structures rather than coordinates. It implements mathematical optimization algorithms as differentiable layers, allow

    Features cost objectives that combine structural relational data and feature distances for complex dataset alignment.

    Pythondomain-adaptationemdgromov-wasserstein
    Auf GitHub ansehen↗2,751
  • rst-tu-dortmund/teb_local_plannerAvatar von rst-tu-dortmund

    rst-tu-dortmund/teb_local_planner

    1,322Auf GitHub ansehen↗

    Teblocalplanner is a robot navigation package and local planner that computes collision-free trajectories for mobile robots in dynamic environments. The software operates as a navigation algorithm designed to calculate optimal paths by continuously balancing execution time, kinematic limits, obstacle clearance, and trajectory smoothness within a moving time window. The system utilizes timed-elastic-band optimization to treat trajectories as elastic bands that deform based on environmental constraints and obstacles. It incorporates graph-based topology generation to explore distinct homotopy

    Balances execution time, kinematic limits, obstacle clearance, and smoothness to generate optimal driving commands.

    C++mobile-robotsnavigationoptimal-control
    Auf GitHub ansehen↗1,322
  1. Home
  2. Artificial Intelligence & ML
  3. Cost Functions

Unter-Tags erkunden

  • Autonomous NavigationMathematical objectives used to weight safety, smoothness, and efficiency in autonomous vehicle path planning. **Distinct from Cost Functions:** Distinct from ML cost functions: focuses on path planning objectives for navigation rather than model training loss.
  • Cost Function CompositionWrapping and combining different types of cost functions to build complex objective functions. **Distinct from Cost Functions:** Focuses on the structural composition of optimization objectives rather than specific ML cost metrics.
  • Cost Function VisualizationsVisual representations of the relationship between model weights and the resulting loss. **Distinct from Cost Functions:** Focuses on the graphical plotting of cost surfaces rather than the mathematical definition of the function
  • Cost-Sensitive ClassifiersTrains models that minimize misclassification cost by learning from examples with per-class cost labels. **Distinct from Cost Functions:** Distinct from Cost Functions: focuses on classification with per-class costs, not general mathematical cost functions.
  • Fused-Cost ObjectivesObjectives that combine multiple cost metrics, such as structural relations and feature distances, into a single alignment goal. **Distinct from Cost Functions:** Focuses on combining topology and attributes, distinct from standard ML error cost functions.
  • Prior DistributionsImplementation of cost functions that penalize deviation from a target value, often used as Bayesian priors. **Distinct from Cost Functions:** Specifically implements squared-distance priors weighted by stiffness, distinct from general ML cost functions.
  • Residual ScalingTransforming individual residuals to adjust their relative weight in the total cost function. **Distinct from Cost Functions:** Focuses on scaling the residual value for optimization robustness rather than ML gradient scaling.
  • Robot Navigation Cost ObjectivesBalances execution time, kinematic limits, obstacle clearance, and smoothness to generate optimal driving commands. **Distinct from Cost Functions:** Distinct from standard ML loss functions: balances kinematic limits and obstacle clearance for robot navigation.