9 Repos
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.