Introduction To Machine Learning — Venar Academy

Based on these machine learning tasks or problems, there are several algorithms used to do these tasks. The commonly used machine learning algorithms are Logistic Regression, Support Vector Machine, Linear Regression, Decision Tree, (SVM), Naive Bayesian, Random Forest, K-Nearest Neighbor (KNN), KMeans e.t.c.

The terminologies used in Machine Learning

• Model
  A model in machine learning is a specific representation derived from data by applying some sort of machine learning algorithm. A model can also be called a hypothesis.
• Feature
  Feature is an individually measurable property of data. A set of numerical features can conveniently be described as a feature vector. Feature vectors are fed into the model as input. For example, you may have features such as color, smell, and taste to predict a fetus.
• Target (also known as Label)
  The target variable or label is the value the model should predict. For the fruit examples discussed in the Functions section, each test case’s label will be a fruit name such as apple, orange, banana, etc.
• Training
  The idea is to provide a set of inputs which are features and expected outputs (labels), so after training we have a model (hypothesis), which maps the new data into one of the categories we train.
• Prediction
  When your model is ready, you can provide an input dataset that will give you predictable results (labels).

The picture shown below illustrates the idea above.

Originally published at https://www.venaracademy.com.