Level -2 Report
29 / 2 / 2024
Decision tree based ID3 Algorithm
Decision tree algorithm is a branch of Machine learning, it is a recursive algorithm which traverses a dataset by keeping a root node and moving onto its branches or child nodes by only considering non-traversed nodes. Click here to know more
Anomaly Detection
A method of machine learning to identify rare events or observations. Used widely in tackling problems like credit card fraud, failing machine in a server, cyber attacks etc. Click here to know more about
Exploratory Data analysis
So Exploratory Data analysis means various ways in which you can unlock secrets from the given data. We have to make sure data is clean, no errors or empty spaces EDA can include many skills and techniques. Click here to know more
Ensemble techniques
Ensemble techniques are used to generate outputs with greater accuracy by using multiple models and taking out weighted mean, majority voting or training another model through obtained results. Click hereto know more.
Image Classification by K-means clustering:
Image classification is the task of grouping images of similar types. See how K-means clustering can be used to achieve that. Click here
Naive Bayesian Classifier:
It is a supervised learning algorithm.It classifies the data point based on independent probabilities of a data point without considering influence of other data points. We need to implement a text classifier using naive bayesian classifier. Click here
Random Forest, GBM and XgBoost
Various ensemble techniques to increase the accuracy of the model. Click here
Support Vector Machine
SVMs are all about finding the best dividing line (or hyperplane in higher dimensions) to separate different classes of data. The \best" means the line that creates the widest possible empty margin between classes. Click here
Hyper parameter tuning
When you’re training machine learning models, each dataset and model needs a different set of hyperparameters, which are a kind of variable. The only way to determine these is through multiple experiments, where you pick a set of hyperparameters and run them through your model. This is called hyperparameter tuning.Click here "