Wanting to know some of the **deep learning algorithms in python **then have a look at the below-given list of algorithms that **Technographx** has brought for you today. They are used for predictions and other applications in ML.

**1) Linear regression **

**Source: wordpress.com**

It is perhaps one of the most well-known algorithms in statistics and machine learning. Linear Regression is represented with an equation that describes a line that best fits the relationship between the input variables (x) and the output variables (y). The relationship between both the variables is fitted perfectly by finding specific weightings for the input variables called coefficients (B).

** 2) Logistic Regression**

**Source: debuggercafe.com**

It is another technique borrowed by machine learning from the field of statistics. It is the go-to method for binary classification problems. It is like linear regression in which the goal is to find the values for the coefficients that weight each input variable. The prediction for the output is done using a non-linear function called the logistic function.

**Source: ytimg.com**

The shape of the logistic functions is like a big S and will transform any value into the range 0 to 1. It is useful as we can apply a rule to the output of the logistic function to snap values to 0 and 1 and predict a class value. The predictions made by logistic regression can be used as the probability of a given data instance belonging to either class 0 or class 1.

It is a very fast model to learn and effective on binary classification problems. This algorithm works better when you remove attributes that are unrelated to the output variable and also the attributes that are very similar to each other.

Also Read:- Awesome Advantages of the Deep Learning Regression Models

**3) Linear Discriminant Analysis**

**Source: digitalvidya.com**

The limitation of Logistic Regression is that it is limited to only two-class classification problems. For more than two classes, the Linear Discriminant Analysis algorithm is the preferred linear classification technique.

It is pretty straight forward to represent LDA. The algorithm consists of statistical properties of your data, calculated for each class. It includes the following things for a single input variable.

- The mean value for each class.
- The variance calculated across all classes.

The predictions are done by calculating a discriminate value for each class and also making a prediction for the class with the largest value.

So, these were the different basic **deep learning algorithms **that are used in machine learning and data science. Machine Learning , AI, Deep Learning are the new buzz all over the world. There are few** best machine learning courses** on the internet that the students are getting to learn for upgrading their skills to the best.

**Source: wordpress.com**