Utkarsh-Bajpai

Brain-Age-Prediction

Compared Bayesian, elastic net, random forest and standard regression using grid search for brain age prediction. Removed outliers, highly correlated features. Used lasso to find relevant features.

CIL-Road-Segmentation

Detecting roads in satellite imagery using deep learning

deeplearning.ai-Coursera

Repository for assignments completed during the Coursera course deeplearning.ai

domain-transfer-network

TensorFlow Implementation of "Unsupervised Cross-Domain Image Generation"

Google-Stock-Prediction-Using-Linear-Regression

Google Stock Prediction Using Linear Regression with an accuracy of 98% and saving the trained classifier using Pickle. It also uses multi-threading to reduce the training time.

Handwritten-Digit-Recognition

A Handwritten Digit Recognition System to evaluate the effectiveness of various types of classifiers such as MLP classifier, K Nearest Neighbour Classifier, SVC, Decision Tree Classifier, Random Forest Classifier, AdaBoost Classifier and GaussianNB in recognising handwritten digits.

HappyBirthdayApp

This is a static app which displays a Birthday Card on the screen.

JustJava

This is a Coffee Ordering app which shows the final amount the user has to pay.

keras

Deep Learning for humans

Parameter-optimization-for-DeepZ-robustness-verification

DeepZ is a method for local robustness verification, based on zonotopes, a type of convex relaxations, and abstract transformations. While affine transformations and convolutions can be represented exactly using this framework, a sound over-approximation has to be used to approximate the ReLU function. The abstract transformer used in DeepZ is parameterized by one parameter per hidden unit. In this work we propose an optimization strategy for this parameterization to increase the maximum verifiable image perturbation for both fully-connected and convolutional network architectures.

Utkarsh-Bajpai/Parameter-optimization-for-DeepZ-robustness-verification

DeepZ is a method for local robustness verification, based on zonotopes, a type of convex relaxations, and abstract transformations. While affine transformations and convolutions can be represented exactly using this framework, a sound over-approximation has to be used to approximate the ReLU function. The abstract transformer used in DeepZ is parameterized by one parameter per hidden unit. In this work we propose an optimization strategy for this parameterization to increase the maximum verifiable image perturbation for both fully-connected and convolutional network architectures.

Utkarsh-Bajpai/Brain-Age-Prediction

Compared Bayesian, elastic net, random forest and standard regression using grid search for brain age prediction. Removed outliers, highly correlated features. Used lasso to find relevant features.

Utkarsh-Bajpai/CIL-Road-Segmentation

Detecting roads in satellite imagery using deep learning

Utkarsh-Bajpai/deeplearning.ai-Coursera

Repository for assignments completed during the Coursera course deeplearning.ai

Utkarsh-Bajpai/domain-transfer-network

TensorFlow Implementation of "Unsupervised Cross-Domain Image Generation"

Utkarsh-Bajpai/Google-Stock-Prediction-Using-Linear-Regression

Google Stock Prediction Using Linear Regression with an accuracy of 98% and saving the trained classifier using Pickle. It also uses multi-threading to reduce the training time.

Utkarsh-Bajpai/Handwritten-Digit-Recognition

A Handwritten Digit Recognition System to evaluate the effectiveness of various types of classifiers such as MLP classifier, K Nearest Neighbour Classifier, SVC, Decision Tree Classifier, Random Forest Classifier, AdaBoost Classifier and GaussianNB in recognising handwritten digits.

Utkarsh-Bajpai/HappyBirthdayApp

This is a static app which displays a Birthday Card on the screen.

Utkarsh-Bajpai/JustJava

This is a Coffee Ordering app which shows the final amount the user has to pay.

Utkarsh-Bajpai/keras

Deep Learning for humans

Utkarsh-Bajpai/Linear-Regression-Mathematics

Implementing Mathematics of Linear Regression from Scratch

Utkarsh-Bajpai/Local-Outlier-Factor

This repository contains our improvements of the algorithm introduced in [1]. Following the course curriculum our efforts concentrated on restructuring, unrolling and vectorizing various elements of the computations. Furthermore we have experimented with different data structures and memory layouts.

Utkarsh-Bajpai/mos

Utkarsh-Bajpai/Name-Generation-and-Classification-using-rnn

Name generation and classification using recurrent neural network

Utkarsh-Bajpai/R-NET-in-Keras

R-NET implementation in Keras.

Utkarsh-Bajpai/Sentdex-ML-Youtube-Tutorials

Repo for code of Practical Machine Learning Tutorial with Python Youtube tutorial by sentdex. The objective of this course is to give a holistic understanding of machine learning, covering theory, application, and inner workings of supervised, unsupervised, and deep learning algorithms.

Utkarsh-Bajpai/STRS

Software Engineering Project-App for booking a mode of trasport.

Utkarsh-Bajpai/TensorFlow-Examples

TensorFlow Tutorial and Examples for Beginners with Latest APIs

Utkarsh-Bajpai/tfjs-examples

Examples built with TensorFlow.js

Utkarsh-Bajpai/theano_exercises

Exercises for my tutorials on Theano

Utkarsh-Bajpai/Utkarsh-Bajpai.github.io

Utkarsh-Bajpai/VQA-tensorflow

Tensorflow Implementation of Deeper LSTM+ normalized CNN for Visual Question Answering

Utkarsh-Bajpai/WhoIsFree

A complete timetable management system for Faculties, Students or any VIT club/chapter.