MACHINE LEARNING ALGORITHMS

hey! Here we will discuss The Machine Learning algorithms and Its type firstly we need to know what is a machine learning algorithm, simply machine is the device we are working on or the system on which we need to perform any operation, and    Algorithm is a process or set of rules which is followed in solving any problem, especially in the computer. So, Machine learning algorithms basically mean how and on what process a system can learn the operations to be performed there are certain rules which a  machine has to follow to learn the processes and techniques which a human being wants the system to learn.

 

MACHINE LEARNING ALGORITHMS can be categorized as supervised or unsupervised  

SUPERVISED ML ALGORITHMS:

 As the name indicates have a supervisor as a teacher. These algorithms apply learning from past data to new data using labeled examples.

Technically, supervised learning algorithms learn an association between input data and output. For example, If we have an input variable(X) and output variable(Y), then the mapping function from input to output can be given as, Y =f(x). This mapping function can be used to predict the output value for any new input after learning from the existing data.

Supervised learning algorithms start with analyzing a known training dataset, to produce an inferred function that can be used to predict future data values. The learning algorithm then compares the predicted output with the actual output to find errors and modify the models accordingly.

For example, if you have a basket filled with various fruits, then the first step is to train the machine to identify the fruit. Now, our machine can easily identify an apple and a banana.

Supervised learning algorithms can be further classified into two categories:

• Classification Algorithm: 

A classification Algorithm classifies data into a particular group of classification techniques and predicts discrete categories. The output will be based on what the model has learned in the training phase.

• Regression: 

A regression Algorithm predicts a real value. The output value is based on what the model has learned in its training phase. In contrast to classification algorithms, regression predicts continuous values for example – The cost of a product, The value of a stock, and the change in temperature commonly used regression algorithms include logistic regression, neural networks, etc.

Thus in a supervised ML algorithm, data input and desired output, along with feedback about the accuracy of prediction during algorithms training are provided.

• Unsupervised Learning: 

 In this case, the ML algorithm works on that information without any guidance. The unsorted information is grouped based on similarities, patterns, and differences without prior data training.

For example- If we give an image of mango and orange, then initially the machine has no idea about what a mango looks like and what the orange looks like.

UNSUPERVISED ML ALGORITHM:  

Unsupervised ML algorithms learn through observation and finding structure in the data. That is the model automatically finds patterns and relationships in the dataset by creating clusters in it.

For example, if given a dataset of pictures of both mangos and oranges, the algorithm can make two clusters- one containing only pictures of oranges and another of mangoes. 

What an unsupervised ML cannot do is specify labels to the clusters. That is, it can only segregate the pictures but cannot tell that this is a real-world orange and that is a mango.

UNSUPERVISED LEARNING  can be categorized into two sets of algorithms:

•  CLUSTERING: In clustering, the aim is to discover inherent grouping in the data or discover hidden patterns. It is one of the most useful unsupervised ML techniques as it finds similarities as well as relationships in the underlying data.
• ASOCIATION ANALYSIS: In association mining, the aim is to discover rules that describe a large portion of data.
• DIMENSIONALITY REDUCTION: It is used to reduce the number of feature variables for the data set. It is done by selecting a set of principles or representative features.
• ANOMALY DEDUCTION: This technique is used to find out the occurrences of rare events and observations that generally do not occur.

 

Thus, UNSUPERVISED ML ALGORITHMS  (also called neural networks) are used when the information used to train is neither classified nor labeled. These algorithms use an iterative approach called DEEP LEARNING to review data and arrive at conclusion.

Unsupervised learning algorithms are used for more complex tasks than supervised learning systems. For example, these algorithms are used in image recognition, speech-to-text, and natural learning language processing applications, predicting the probability of the presence of a particular disease, etc.….