Machine Learning (2026) | Platforms, Frameworks, MLOps, AutoML & Model Serving

Learn ML: Algorithms, Applications & Resources

14 entries

Core concepts, algorithms and where machine learning is applied.

01Machine Learning ModelsLogistic regression, random forests, CatBoost, XGBoost and tabular foundation models such as TabPFN-3.5. 02Machine Learning AlgorithmsA reference guide to core ML algorithms — from linear regression and decision trees to SVMs, clustering, and ensemble methods. 03Machine Learning ApplicationsReal-world applications of machine learning across healthcare, finance, retail, manufacturing, and other industry verticals driving transformation. 04AI & Machine Learning ResourcesCurated AI explainers, machine learning tutorials and courses, and official AI learning tracks for self-directed learners. 05Deep LearningDeep learning frameworks, datasets and graph neural networks. 06Reinforcement LearningReinforcement learning hub with guides and algorithms. 07Reinforcement Learning GuideGuide to reinforcement learning. 08Reinforcement Learning AlgorithmsValue-based, policy-based and actor-critic algorithms, plus RLHF, GRPO, offline RL and libraries. 09Federated Learning GuideGuide to federated learning. 10Graph Neural NetworksGraph neural networks: learning from connected data. 11Time-Series Forecasting AlgorithmsARIMA, ETS, Prophet, XGBoost and deep learning forecasters. 12Causal AI ModelsCausal inference, causal discovery, DoWhy, EconML and learning resources. 13Top Machine Learning JournalsTop machine learning journals and publication venues. 14Data MiningClassification, clustering, association rules and anomaly detection, with software, datasets, books and conferences.

Frameworks, Libraries & Platforms

13 entries

Where models get built: frameworks, language libraries and end-to-end platforms.

15Machine Learning PlatformsEnd-to-end platforms for building, training, deploying, and managing ML models at scale across cloud and on-premises environments. 16Machine Learning FrameworksCore libraries and frameworks powering ML model development — covering TensorFlow, PyTorch, scikit-learn, XGBoost, and beyond. 17Machine Learning LibrariesComprehensive reference to ML libraries across Python, R, Java, Scala, and other languages commonly used in research and production ML systems. 18AI Development FrameworksAI development frameworks such as TensorFlow, PyTorch and Keras. 19Deep Learning FrameworksFrameworks for building and training deep neural networks. 20Deep Learning PlatformsTensorFlow, PyTorch, Keras, JAX, PaddlePaddle, MindSpore and other deep learning platforms. 21Federated Learning FrameworksFrameworks for federated learning across distributed data. 22JavaScript Machine Learning LibrariesML libraries for JavaScript and Node.js — bringing model training and inference directly to the browser, server, and edge environments. 23Machine Learning Frameworks in JuliaML frameworks and libraries available in the Julia programming language — valued for its high-performance numerical computing and Python-like developer experience. 24Python Libraries for Data ScientistsPython libraries for data science work. 25No-Code ML PlatformsDrag-and-drop and low-code platforms that let non-developers build, evaluate, and deploy ML models without writing code. 26AutoML ToolsTools that automate the ML pipeline — from feature engineering and model selection to hyperparameter tuning and neural architecture search. 27Data Science PlatformsPlatforms for data science workflows, from Dataiku to KNIME.

Data & Features

8 entries

Datasets, feature engineering and the stores that feed models.

28Data Sets for ML/DLCurated public and commercial datasets for training, fine-tuning, and benchmarking machine learning and deep learning models across domains. 29Databases for AI ModelingDatabase systems optimised for machine learning workloads — from vector databases and feature stores to graph and time series databases. 30Vector DatabasesVector databases for embeddings and similarity search. 31Enterprise Data Catalogs for DataOpsData catalog platforms for discovering, documenting, versioning, and governing datasets across ML and enterprise data teams. 32Feature Store SolutionsCentralized repositories for storing, sharing, and serving ML features — enabling reuse across teams and consistent training-serving parity. 33ML Feature Engineering ToolsTools for transforming raw data into informative features that improve machine learning model accuracy, generalisability, and performance. 34ML Metadata Store SolutionsSolutions for storing and querying ML metadata — experiment parameters, metrics, model versions, artifacts, and lineage information. 35Feature Engineering: Approaches & ToolsTechniques for imputation, encoding, scaling, selection and domain features, with libraries, feature stores and data quality tools.

Training, Tuning & Pipelines

3 entries

Automating hyperparameter search, workflows and continuous training.

36ML HyperParameter Optimization ToolsTools for automating the search for optimal model hyperparameters — covering grid search, random search, Bayesian optimization, and neural architecture search. 37ML Workflow Orchestration ToolsTools for orchestrating and automating multi-step ML pipelines — from data preparation and training through evaluation and production deployment. 38Continuous Machine Learning (CML) FrameworksFrameworks for applying CI/CD principles to ML — automating model retraining, evaluation, and deployment in response to data and code changes.

MLOps, Deployment & Serving

7 entries

Operationalising models: platforms, lifecycle management and serving.

39MLOps PlatformsPlatforms that operationalise machine learning — covering experiment tracking, model deployment, pipeline automation, and lifecycle management. 40Open Source MLOps PlatformsOpen source tools for MLOps workflows — including Kubeflow, MLflow, DVC, Feast, and other community-driven solutions for model operations. 41ModelOps PlatformsPlatforms for operationalising AI/ML models at enterprise scale — covering deployment, lifecycle management, governance, versioning, and monitoring. 42ML Model Serving ToolsTools and infrastructure for serving ML models in production — covering batch inference, real-time scoring, and model deployment at scale. 43Production AI Inference StackvLLM, llm-d, prefill/decode and GPU load balancing for inference. 44Kubernetes Tools for MLKubeflow, KServe, Seldon Core and other Kubernetes tools for ML. 45LLMOpsOperating LLM applications in production.

Monitoring & Observability

3 entries

Watching models in production for drift, degradation and fairness.

46ML Model Observability PlatformsPlatforms for observing ML model behaviour in production — tracking data drift, prediction distributions, and model health over time. 47ML Model Monitoring ToolsTools for monitoring deployed ML models for performance degradation, data drift, concept drift, and fairness issues in real-time. 48Explainable AI (XAI) FrameworksSHAP, LIME, InterpretML, Captum, Alibi and other tools for explaining model behavior.

Frequently Asked Questions

What is machine learning?

Machine learning is a branch of AI in which algorithms learn patterns from data to make predictions or decisions without being explicitly programmed for each case. Typical tasks include classification, regression, clustering and recommendation.

What is MLOps?

MLOps applies DevOps practices to machine learning: versioning data and models, automating training and deployment pipelines, and monitoring models in production so they stay accurate. The MLOps and Open Source MLOps pages list the platforms.

What is the difference between a framework and a platform?

A framework such as PyTorch or scikit-learn is a library you use to write and train models. A platform adds managed infrastructure, experiment tracking, deployment and governance around those frameworks.

Why do teams use a feature store?

A feature store keeps one governed copy of the features used for training and serving, so models see consistent inputs in both places and teams can reuse features instead of rebuilding them.

What should I monitor once a model is deployed?

Track prediction quality, input data drift, concept drift, latency and fairness. The monitoring and observability pages list tools that alert when a model begins to degrade.

Machine Learning Platforms, Frameworks & MLOps