peterindia.net
Home · AI Paradigms

Self-Learning Algorithms

Five ways a system can get better at a task from data or experience, instead of being handed an explicit rule for every case — each with its own home page, and its own place in a production AI stack.

5Learning Paradigms
60+Linked Deep-Dive Pages

OverviewWhat Makes an Algorithm "Self-Learning"?

A self-learning algorithm improves its own behaviour by processing data or experience, rather than following logic a programmer wrote by hand for every case. That single idea splits into five distinct paradigms below — and they aren't mutually exclusive. A deep neural network is a kind of machine learning model; several models can be combined into an ensemble; a reinforcement learning agent can itself be a deep network; and federated learning is a training arrangement that can apply to almost any of the others, training a shared model across many devices or institutions without centralizing their data.

MACHINE LEARNING Deep Learning Multi-layer neural networks Ensemble Combines many models into one classical models · trees · linear · SVMs · clustering REINFORCEMENT LEARNING Learns from reward, not labelled data — its own paradigm, though its agent is often a deep network FEDERATED LEARNING — a training arrangement that applies across all of the above
Deep Learning and Ensemble Learning live inside Machine Learning; Reinforcement Learning is its own paradigm; Federated Learning cuts across all three.

The Five ParadigmsWhere to Go Deeper

Each card links to its own home page on peterindia.net, curating platforms, frameworks, algorithms, and resources for that paradigm specifically.

01

Machine Learning

The broad discipline of models that learn statistical patterns from data — the parent category that deep learning and ensemble methods both sit inside.

This site covers: 26 topics — platforms, frameworks, algorithms, MLOps, AutoML, feature stores, model serving, observability
Explore Machine Learning ↗
02

Deep Learning

Machine learning with multi-layered neural networks, which learn their own feature representations directly from raw data instead of needing them hand-engineered.

This site covers: 9 topics — frameworks, algorithms (CNNs, RNNs, Transformers), applications, datasets, GNN and graph libraries
Explore Deep Learning ↗
03

Reinforcement Learning

An agent learns by acting, observing, and being rewarded — no labelled dataset required. The paradigm behind game-playing agents, robotics control, and the RLHF pipelines that align large language models.

This site covers: the agent–environment–reward loop, core vocabulary, why it matters in 2026, and algorithm references
Explore Reinforcement Learning ↗
04

Ensemble Learning

Combining many individually weaker models — through bagging, boosting, or stacking — into a single predictor that generalizes better than any one model alone.

This site covers: ensemble methods within the Machine Learning Algorithms reference — a dedicated Ensemble Learning page is not yet published
See Ensemble Methods ↗
05

Federated Learning

A privacy-preserving training arrangement where a shared model learns across distributed devices or institutions without the raw data ever leaving its source — only model updates are exchanged and aggregated.

This site covers: FedAvg and advanced optimisation, statistical & system heterogeneity, privacy & security, personalization, tools
Explore Federated Learning ↗