Machine learning (ML)

The term “machine learning” is a subfield of AI, where a machine learns and improves from experience without any explicit programming. Machine learning does this through various algorithms like artificial neural networks, support vector machines, decision trees, and genetic algorithms. A model is developed on a subset of data called the training set and further tested and validated on another subset or unseen data. Nevertheless, these techniques have limitations in processing natural data such as images, etc. These lacunae inspired another subset of machine learning called deep learning. Many kinds of tasks can be solved with machine learning. Some of the most common machine learning tasks include the following: classification, classification with missing inputs, regression, transcription, machine translation, structured output, prediction, anomaly detection, synthesis and sampling, imputation of missing values, denoising, density estimation, etc.