Sahil N Digikar's Projects
A Classification problem, given text review to determine whether the review is +ve or -ve using various ML algorithms. Here we are finding the model that peforms well using AUC as a metric.
The goal of anomaly detection is to identify cases that are unusual within video data.
TensorFlow code and pre-trained models for BERT
A movie information APP that displays a list of movies from The Movie Database (TMDb) API. The app shows top movies for each year and users can filter by genre, the app also loads top movies from previous / next years as the user scrolls through the list in both direction.
Experimented with different architectures and kernels on MNIST dataset using Convolutional Neural Networks.
Identify which questions asked on QUORA are duplicated on question that have already been asked. Used performance metric as log loss and trained the model using XGBOOST that brought my log loss to 0.3157.
To find number of pickups, given location coordinates(latitude and longitude) and time, in the query region and surrounding regions.
Given a directed social graph, have to predict missing links to recommend users.
Implemented Stochastic Gradient Descent linear Regression on Boston House Price Data. Here we have also implemented SGD using python code. At last we are comparing the weights obtained by Sklearn's LinearRegression with Sklearn's SGDRegressor along with our own python implementation of SGDRegressor.
A simple micro-frontend project to understand module federation plugin
Experimented with different architectures on MNIST dataset using MLPs with different dropouts.
Classify the given genetic variations/mutations based on evidence from text-based clinical literature.
Suggest the tags based on the content that was there in the question posted on Stack Overflow. Used performance metric as micro F1 score and trained models by using One VS Rest Logistic Regression and Linear SVM