Shreesha\'s AIML-Level-1 report

14 / 9 / 2023

Task 1: Linear and logistic regression with the help of scikit:

Linear regression maps a linear relation between 2 variables and Logistic regression predicts the outcome of an event which has a yes or no, 0 or 1 kind of result. Check the code here

Task 2: Matplotlib and visualizing dataset

Visualizing the dataset is very important in selecting the model to train. For example If the relationship between 2 variables is Linear we select linear regression model. Matplotlib library is one of the best and simple libraries out there. It is beginner friendly and consists of many plots. Check the full report here

Task 3: Metrics and performance evaluation:

We can't really improve if we don't know the mistakes. Its the same case for our Machine learning models, here comes metrics evaluators such as MS MSE and R2 I evaluate both the classification and regression models which I have trained in task 4. More info about Metrics can be checked here

Task 4: Linear and Logistic regression from scratch:

In task 1, I had already trained a linear and logistic regression model but using scikit algorithm. But in this task I train a model of linear and logistic regression from scratch in python. checkhere

Task 5: K-Nearest Neighbours

The k-nearest neighbors algorithm, also known as KNN or k-NN, is a non-parametric, supervised learning classifier, which uses proximity(distance between points) to make classifications or predictions about the grouping of an individual data point. Check the code here

Task 6: An elementary step towards neural networks

Neural networks are a kind of data structures which are inspired by human brain. A blog on it can be found here. Next part of the task is to understand GPT and write a blog on it Check it out here

Task 7: Math behind Machine learning

In this task, we need to perform curve fitting for a suitable data and fourier transform Check it out here

Task 8: Data Visualisation

Matplotlib is one of the basic libraries for Data visualisation. Plotly takes it to next level. It has more advanced plots than Matplotlib and it is also one of highly regarded libraries in machine learning domain. Check out the plots here

Task 9: Introduction to the Decision trees:

A decision tree is a flowchart-like structure in which each internal node represents a \test" on an attribute (e.g. whether a coin flip comes up heads or tails), each branch represents the outcome of the test, and each leaf node represents a class label (decision taken after computing all attributes).Check more about it here

Task 10: Real world application of Machine learning

It is true that industrial models of machine learning are way advanced and different than the above ones. One of them are recommendation systems. Check more about them here

Thank you

"