Linear regression is one of the regression-based algorithms in ML. It shows a linear relationship between its variables.<\/p>\n
There is a mathematical formula to represent linear regression.<\/p>\n
y = m*x + c<\/strong><\/p>\n This is the representation of a line in mathematics. This means that the data points would be around this line in the graph.<\/p>\n Here, y and x are the axes, m is the slope and c is the constant<\/em>.<\/p>\n There are two types of Linear regression.<\/p>\n Simple linear regression includes only one input variable.<\/p>\n An example can make this easier.<\/p>\n The price of a house can be predicted by using just it\u2019s size. Whereas, multiple linear regression is different.<\/p>\n It takes in various types of input for prediction. Here, other criteria like distance of the house from city, size and many others matter.<\/p>\n In mathematical terms, we can represent linear regression as:<\/p>\n F(x) = b0 + b1x1 + b2x2 + b3x3 +\u2026\u2026\u2026.+ bkxk<\/strong><\/p>\n This is another type of regression. It does not include a linear graph, as the graph is a curve here.<\/p>\n It is a classification-based algorithm<\/strong> and it is used for giving predictions. Here, the graph is a sigmoid function.<\/p>\n Sigmoid<\/strong> means that the graph is S-shaped<\/strong>.<\/p>\n Unlike linear regression, here, the dependent variable is binary in nature. Binary means value is either one or zero, or true or false.<\/p>\n We can have the graph images for better understanding: In linear regression, the values can exceed the limit of 0 and 1.<\/p>\n However, logistic regression is based on probability.<\/p>\n Therefore, the values of logistic regression are always between 0 and 1.<\/p>\n Logistic regression is used in many areas. It can be used in the medical sector.<\/p>\n It can classify cancer as potent or less severe. In addition, it can give uncertain values between 0 and 1.<\/p>\n For<\/strong> example<\/strong>, it can help to predict the resemblance between two objects.<\/p>\n There is a mathematical way to represent logistic regression:<\/p>\n S(x) = 1 \/ (1 + e-(F(x))<\/sup>)<\/strong><\/p>\n Here, F(x) is the linear function.<\/p>\n We can also say that the linear function is the logarithmic function of the sigmoid function.<\/p>\n Ln(S(x) \/ (1 \u2013 S(x) ) = F(x)<\/strong><\/p>\n There are two types of logistic regression:<\/p>\n Project:<\/strong> Please refer Credit Card Fraud Detection Project<\/strong> <\/em><\/a>for the implementation of logistic regression algorithm.<\/p>\n LSTM or Long Short Term Memory<\/strong> is a great substitute for RNNs or Recurrent Neural Networks<\/strong>.<\/p>\n The reason is RNNs are called feed-forward neural networks.<\/p>\n Feed Forward means that they always tend to move forward. They do not remember any previous information.<\/p>\n If you want to add any new piece of data, it will overwrite the existing data. RNNs have something called Short Term Memory<\/strong>.<\/p>\n This short-term memory prevents them from storing data. In addition, RNNs cannot differentiate between important and less useful information.<\/p>\n This is different in LSTM. They have certain cell states within them.<\/p>\n The information, which we give, passes through these states. These cell states help to separate out useful and non-useful information.<\/p>\n This means that LSTM can remember or forget things. There are also three dependencies in these cells:<\/p>\n These are the states, which help LSTM to remember and make decisions.<\/p>\n We can take an example of the stock market for better understanding. LSTM can be of great use in stock predictions.<\/p>\n As per these states, we can see the previous performance and price of stocks. We can also see the current performance of the stocks.<\/p>\n Therefore, using the previous and present information, we can predict stock prices.<\/p>\n Project:<\/strong> Please refer Image Caption Generator<\/strong>\u00a0Project<\/strong><\/em><\/a> for the implementation of the LSTM algorithm.<\/p>\n A decision tree is a tree structure used in ML. This tree helps in many classification techniques.<\/p>\n These trees are used in various algorithms. Like, take CART as an example.<\/p>\n CART or classification and regression technique<\/strong> use decision trees. We have the Gini-index with which we can evaluate the cost function of CART.<\/p>\n Decision trees are generally binary trees. So, each node will only have two possibilities.<\/p>\n It is basically an if-then-else structure that is continuous in nature. Decision trees are based on supervised learning<\/strong>.<\/p>\n They are one of the easiest and efficient to use Machine Learning algorithms.<\/p>\n There are various applications of decision trees that form the base of several ML models. It is mainly used in the medical sector.<\/p>\n So, it can classify the disease as dangerous or mild. This was only one example.<\/p>\n We can use it in any of the fields today, like education, business, etc.<\/p>\n Project:<\/strong> Please refer Parkinson\u2019s Disease Detection Project<\/strong><\/em><\/a> for the implementation of Decision Trees Algorithm.<\/p>\n A random forest is a collection of decision trees. It is a much bigger and robust version of the decision tree.<\/p>\n The reason is we can take in more information than a decision tree. The problem of overfitting in decision trees can be removed here.<\/p>\n They work in a specific way as mentioned. There is a huge training dataset.<\/p>\n This dataset is divided into smaller subparts. The algorithm of random forest creates decision trees for these datasets.<\/p>\n For each decision tree created, we obtain different results. The algorithm does a voting procedure on the results obtained.<\/p>\n The best result obtained from the votes is the final prediction obtained. This reduces the problem of overfitting in one decision tree.<\/p>\n We should also know that the algorithm has a high complexity. It is a big Machine Learning algorithm and takes a lot of time to build.<\/p>\n Also, it takes a lot of computational power to execute. The process can give accurate results, but it is very time-consuming.<\/p>\n Reinforcement learning is a technique mainly used in Deep Learning and neural networks.<\/p>\n This method trains the ML models to make decisions.<\/p>\n This is mostly used in areas like gaming, automated cars, etc. Here models work on the basis of rewards given.<\/p>\n The algorithm gives the model a reward if it achieves the right result.<\/p>\n We can explain the working of RL with an example.<\/p>\n Suppose we are teaching our dog some commands. The commands will be, sit, run, etc.<\/p>\n At first, we will try to emulate the situation ourselves. The dog may respond in many ways.<\/p>\n If it is the right way, we give biscuits to the dog as a reward. So, the next time, if there is a similar situation, the dog might do it more eagerly.<\/p>\n This is how the dog learns.<\/p>\n This is what RL is. The algorithm gives rewards to the model, on getting the right result.<\/p>\n This reward giving is called feedback<\/strong>. There can be different varieties of feedback based on your choice.<\/p>\n There are also negative feedbacks along with positive ones. If the dog does not follow properly, we shout at it.<\/p>\n The shout here gives the dog an idea of not repeating the same thing. This is how many games and self- driving cars are designed.<\/p>\n There are three types of RL algorithms:<\/p>\n We also have two types of RL models.<\/p>\n These are the Q learning<\/strong> and Markov<\/strong> decision process.<\/p>\n It is a very vast topic to cover and is currently under research.<\/p>\n Companies like Amazon<\/strong>, Google<\/strong> are working on it.<\/p>\n K-means clustering is an unsupervised learning approach. In this type of Machine Learning algorithm, we analyze clusters of data.<\/p>\n Here, k is the number of centroids in the dataset. Means is the mean or average of these selected k number of centroids.<\/p>\n These centroids can be both real and imaginary based on the data given.<\/p>\n Now, let us try to understand how the algorithm works.<\/p>\n In k-means clustering, the algorithm selects some random points in the dataset. Then it performs iterative operations on these points.<\/p>\n These selected centroids are the starting points of every cluster. These iterations compare each point\u2019s distance with the centroids.<\/p>\n The point gets into the cluster whose centroid is nearest to it. The iterations carry on until all the clusters are formed.<\/p>\n This can be shown in the diagram. The black dots are the centroids of the clusters. This is before the iterative operations take place.<\/p>\n The algorithm selects three random points from the dataset. When the iteration starts, the points start accumulating around centroids near to them.<\/p>\n After the iteration is complete, the image would look like this one below. This Machine Learning algorithm is used in many places. It can be used in areas like image classification, market analysis, etc.<\/p>\n There are several disadvantages like:<\/p>\n\n
2. Logistic Regression<\/h3>\n
![\"machine](\"https:\/\/techvidvan.com\/tutorials\/wp-content\/uploads\/sites\/2\/2020\/02\/logistic-regression.jpg\")
<\/a><\/p>\nA. Linear Regression
<\/a><\/h4>\nB. Logistic Regression<\/h4>\n
\n
3. LSTM Algorithm<\/h3>\n
\n
4. Decision Trees<\/h3>\n
5. Random Forest<\/h3>\n
6. Reinforcement Learning<\/h3>\n
\n
7. K-means Clustering<\/h3>\n
<\/a><\/p>\n<\/a><\/p>\n