Machine Learning (ML)

Full definition

Tom Mitchell's classic definition is: "A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E." ML methods include supervised learning (labeled data), unsupervised learning (unlabeled data), self-supervised learning (labels derived from the data itself), and reinforcement learning (trial and reward).

Why it matters

ML is the engine behind most production AI today — fraud detection, recommendation, demand forecasting, churn prediction, and language understanding. Replacing hand-written rules with learned models often improves accuracy on tasks where the underlying patterns are too complex to specify by hand.

Example

A bank trains a gradient-boosted tree on millions of past transactions, each labeled fraud or legitimate. Once deployed, the model scores new transactions in real time and flags those above a chosen risk threshold.

Next steps

• Get a free workflow map →We map one of your workflows and give you a written verdict: software, a process change or AI. No obligation.
• AI consulting cost guide →Hourly rates and project budgets by firm tier, from independents to the Big Four.

Related terms

• Artificial Intelligence (AI)
  Artificial Intelligence (AI) is the field of computer science focused on building systems that perform tasks typically requiring human intelligence — including learning from data, reasoning under uncertainty, recognizing patterns, understanding language, and making decisions.
• Deep Learning
  Deep Learning is a class of machine learning that uses neural networks with many layers ("deep" architectures) to learn hierarchical representations directly from raw data such as images, audio, or text.
• Supervised Learning
  Supervised learning is the machine-learning paradigm in which a model learns from training examples paired with correct labels, then predicts labels for new, unseen inputs — the dominant approach in production ML today.
• Unsupervised Learning
  Unsupervised learning is a machine-learning paradigm where a model is given only inputs — no labels — and must discover structure in the data: clusters, density, low-dimensional representations, or anomalies.
• Training Data
  Training data is the curated dataset used to teach a machine-learning model — every pattern the model can recognize, every bias it inherits, and every limit to its accuracy ultimately traces back to this data.

More fundamentals terms

• Neural Network
  A neural network is a machine-learning model composed of layers of interconnected nodes ("neurons") whose numerical weights are adjusted during training so the network maps inputs to desired outputs.
• Algorithm
  An algorithm is a finite, well-defined sequence of computational steps that takes an input and produces an output, designed to solve a class of problems — for example, sorting a list, ranking search results, or training a neural network.