The Key ML Tasks

- Overview

Machine learning (ML) is a subset of artificial intelligence (AI) that enables computers to learn from data and improve their performance over time without being explicitly programmed. Although ML is a vast field, all its components have a special significance in their work. 

ML has revolutionized the field of AI by enabling computers to learn from data and enhance their capabilities without the need for explicit programming. In the broad field of ML, different technical components come together to build ingenious solutions and applications.

The 4 core ML Tasks: 

• Classification: Classification is a supervised ML method where the model tries to predict the correct label of a given input data. In classification, the model is fully trained using the training data, and then it is evaluated on test data before being used to perform prediction on new unseen data.
• Regression: Regression is a supervised ML technique which is used to predict continuous values. The ultimate goal of the regression algorithm is to plot a best-fit line or a curve between the data. The three main metrics that are used for evaluating the trained regression model are variance, bias and error.
• Clustering: Clustering is a ML technique that groups similar data points in large datasets. It's also known as unsupervised ML. In ML too, we often group examples as a first step to understand a subject (data set) in a ML system. Grouping unlabeled examples is called clustering.
• Embeddings: Embeddings represent real-world objects, like words, images, or videos, in a form that computers can process. Embeddings enable similarity searches and are foundational for AI.

- The Most Common Types of ML Tasks

Below are some of the most common ML tasks that one may encounter when trying to solve a ML problem. A set of machine learning methods that can be used to solve these tasks is also listed.

ML is about approximating mathematical functions (equations) that represent real-world scenarios. These mathematical functions are also called "mathematical models" or simply models. 

• Embedding
• Searching
• Regression
• Classification
• Clustering
• Transcription
• Machine translation
• Anomaly detection
• Synthesis & sampling
• Estimation of probability density and probability mass function
• Similarity matching
• Co-occurrence grouping
• Causal modeling
• Link profiling