Introduction to Machine Learning

A machine learning model is a file that has been trained to recognize certain types of patterns. You train a model over a set of data, providing it an algorithm that it can use to reason over and learn from those data.

A machine learning model is defined as a mathematical representation of the output of the training process.  

Machine Learning Algorithm Vs Model 

An algorithm in machine learning is a procedure that is run on data to create a machine learning "model"

Machine Learning algorithms performs " pattern recognizance". Algorithms " learn" from data or are fit on a data set.

There are many machine learning algorithms.

A model in machine machine learning is the output of a machine learning algorithm run on a data set.

A model represents what was learned by a machine learning algorithm.  

                                                Image Source: www.cogitotech.com

 Dataset 

A ML dataset is a collection of data that is used to train the model.

A dataset acts as an example to teach the machine learning algorithms how to make predictions.

Types of ML/AI datasets 

1. Training data (60%): This is the data that will be be used to train the model 

2. Validation data(20%): Subset of the training dataset used to check the accuracy of the model.

3. Testing data(20%): Separate set of data from the validation and training datasets, used to evaluate the performance of the model. 

Hypothesis

It is defined as the approximate function that best describes the target in supervised machine learning.

It is primarily based on data as well as bias and restrictions applied to data. Two types of hypothesis are: Null Hypothesis and Alternative Hypothesis.

Hypothesis Space

It is the set of all the possible legal hypothesis. This is the set from which the ML algorithm would determine the best possible (only one) which could best describe the target function or the outputs.

 Inductive Bias

The inductive bias of a learning algorithm is the set of assumptions that the learner uses to predict outputs of given inputs that it has not encountered.

In ML, one aims to construct algorithms that are able to learn to predict a certain target output.

                                         Image source: https://miro.medium.com