Shivam Yadav's Projects
The gaming bot consist of 3 different games that have involved bots , for snake game, here Deep Q learning implementation that updates Q values for every step, then we have Pong game, where bot follows Artificial Intelligence algorithm for its movements in that specific environment. Thus, we also added GUI implementation of that game using tkinter and games over pygame module of Python.
The task here is to clean tweets of given data into json format using python.
using correlation coffecient , here I implemented recommendation system
A data structure is a named location that can be used to store and organize data. And, an algorithm is a collection of steps to solve a particular problem. Learning data structures and algorithms allow us to write efficient and optimized computer programs.
Predict Loan Eligibility for Dream Housing Finance company Dream Housing Finance company deals in all kinds of home loans. They have presence across all urban, semi urban and rural areas. Customer first applies for home loan and after that company validates the customer eligibility for loan. Company wants to automate the loan eligibility process (real time) based on customer detail provided while filling online application form. These details are Gender, Marital Status, Education, Number of Dependents, Income, Loan Amount, Credit History and others. To automate this process, they have provided a dataset to identify the customers segments that are eligible for loan amount so that they can specifically target these customers.
My own leetcode solutions by python
Python & JAVA Solutions for Leetcode
LeetCode
Task: The given dataset contains details about organic chemical compounds including their chemical features, isomeric conformation, names and the classes in which they are classified. The compounds are classified as either βMuskβ or βNon-Muskβ compounds. Your task is to build a classification model on the given data using any Deep Learning approach that you deem appropriate viz. Multi-Layer Perceptron, CNN, RNN, etc. or you could also use transfer learning approaches through selection of appropriate pre-trained model. The data has to be split in a 80:20 ratio for training and validation datasets. You can perform whatever preprocessing and post-processing operations on the data that may help you improve the performance of your model. You are required to report the performance measures of the model viz. Accuracy( Training and Validation) and Loss(Training and Validation) graphs, F1 score, precision, recall, etc. along with a well detailed report of what models, pre-processing, post-processing approaches you have used and why you chose to use these approaches.
Config files for my GitHub profile.
AI Agent that learns how to play Snake with Deep Q-Learning
It is a basic classification problem in which, we have to determine whether a house is sold or unsold on the basis of given features. Here, I am using basic Artificial Neural Network.
Forecasting closing stock price using Tata Global dataset from Quandl. Applying Recurrent Neural Network onto it for predictions.
This task aims to fetch Top 5 articles from internet and show related keywords, titles with it.
The project aims to research around US House Market, and seek for variable that influence USA House prices. Also, to predict house price index for next 20 years.