# Niverel

### Site Tools

en:mathematics:data-analysis:ml:start

# Machine learning

Machine learning has become a key technique for solving problems in computational finance, for credit scoring and algorithmic trading; in image processing and computer vision, for face recognition, motion detection, and object detection; in computational biology, for tumor detection, drug discovery, and DNA sequencing; in energy production, for price and load forecasting; in automotive, aerospace, and manufacturing, for predictive maintenance; and in natural language processing, for voice recognition applications.

Machine learning (ML) is the study of algorithms and statistical models that computer systems use to perform a task without using explicit instructions, relying on models and inference instead. Huh? Machine learning is a technique that teaches computers to do what comes naturally to humans and animals: learn from “experience”. Machine learning algorithms use computational methods to “learn” information from data without relying on a predetermined equation as a model. Huh? It “sees” the input, it “sees” the associated output, and based on computational methods, builds the equation/model as it were, with which it can then predict outcomes for new inputs. The algorithms adaptively improve their performance as the number of samples available for learning increases.

Two types of computational methods are used:

• Supervised learning, which trains a model on known input and output data so that it can predict future outputs. Supervised learning usually uses one of two techniques to develop predictive models.
• Classification techniques predict discrete responses. For example, whether an email is genuine or spam, or whether a tumor is cancerous or benign.
• Regression techniques predict continuous responses. For example, changes in temperature or fluctuations in power demand.
• Unsupervised learning, which finds hidden patterns or intrinsic structures in input data.
• Clustering is used for exploratory data analysis to find hidden patterns or groupings in data.

Deep learning is a specialized form of machine learning in which a computer model learns to do classification tasks directly from images, text, or sound. Deep learning models can achieve state-of-the-art accuracy, sometimes exceeding human-level performance. Models are trained by using a large set of labelled data and neural network architectures that contain many layers.