utkarshsrivastava Goto Github PK

allparallelspf

All versions of Parallel Sparse matrices , We have been working on

benefitspreview

bloomsfilter

increasing the fficiency of a blooms filter further by adding 3 cache to it

cypress-cucumber-example

Example of using Cypress with Cucumber

cypress-example-kitchensink

This is an example app used to showcase Cypress.io testing.

cypress_testing

digit-recognition

Given a data set of images, We use regression to map an image of a hand written digit with the digit

frugalclassifier

One major problem often faced by the machine Learning community is the process of collecting proper test and training data .. It is especially very expensive, time consuming and combursome when human interaction and recordings are involved. And even after a great deal of effort has been put into collecting this data, a great classifier can not be guaranteed. This Classifier greatly reduces this burden by performing classification "on the fly" and dynamically checks the kind of data it requires to improve it's own accuracy ! The classifer works on the principle of multi-level and best of three principle , to sort results into one or more classes. It simultaneously recognizes those classes , for which the accuracy of classification is above or below a pre-defined threshold. As long as a given class's accuracy is below the threshold "T", the classifer keeps demanding training data and test data to improve its accuracy for that class. However, As soon as the accuracy( error component) for a given class reaches above the threshold, it is segregated into a separate bag called the "safe bag". The classes in the safe bag are given less emphasis compared to the "un-safe" classes. test and training data for safe classes are only occasionally and randomly demanded. Un-safe classes are regularly scrutinized anf given much more "training and test data" to improve their accuracy. We continue to perform the above steps until all the classes have reached an accuracy > T. FYI, I am still working on some aspects of the classifier , so the corresponding classes may be temporarily unavailable.

ir_seachengine

ir_searchengine

This is the starter code and tests for CSE 535 Fall 2014 Project 1

mimir

The Mimir probabilistic database overlay

newsarticlepersonalization

https://www.youtube.com/watch?v=rUu7DEbPico

onlineclinic

Designed a web application called Online clinic using Servlets, JSP, HTML, Javascript & Oracle 11g SQL that handles and semi-automates transactions between patients, doctors, facilities and payments

parallelsparsematrixfactorization

Sparse Matrix Factorization (SMF) is a key component in many machine learning problems and there exist a verity a applications in real-world problems such as recommendation systems, estimating missing values, gene expression modeling, intelligent tutoring systems (ITSs), etc. There are different approaches to tackle with SMF rooted in linear algebra and probability theory. In this project, given an incomplete binary matrix of students’ performances over a set of questions, estimating the probability of success or fail over unanswered questions is of interest. This problem is formulated using Maximum Likelihood Estimation (MLE) which leads to a biconvex optimization problem (this formulation is based on SPARFA [4]). The resulting optimization problem is a hard problem to deal with due to the existence of many local minima. On the other hand, when the size of the matrix of students’ performances increase, the existing algorithms are not successful; therefore, an efficient algorithm is required to solve this problem for large matrices. In this project, a parallel algorithm (i.e., a parallel version of SPARFA) is developed to solve the biconvex optimization problem and tested via a number of generated matrices. Keywords: parallel non-convex optimization, matrix factorization, sparse factor analysis 1 Introduction Educational systems have witnessed a substantial transition from traditional educational methods mainly using text books, lectures, etc. to newly developed systems which are artificial intelligent- based systems and personally tailored to the learners [4]. Personalized Learning Systems (PLSs) and Intelligent Tutoring Systems (ITSs) are two more well-known instances of such recently developed educational systems. PLSs take into account learners’ individual characteristics then customize the learning experience to the learners’ current situation and needs [2]. As computerized learning environments, ITSs model and track student learning states [1, 6, 7]. Latent Factor Model and Bayesian Knowledge Tracing are main classes in ITSs [3]. These new approaches encompass computational models from different disciplines including cognitive and learning sciences, education, 1 computational linguistics, artificial intelligence, operations research, and other fields. More details can be found in [1, 4–6]. Recently, [4] developed a new machine learning-based model for learning analytics, which approximate a students knowledge of the concepts underlying a domain, and content analytics, which estimate the relationships among a collection of questions and those concepts. This model calculates the probability that a learner provides the correct response to a question in terms of three factors: their understanding of a set of underlying concepts, the concepts involved in each question, and each questions intrinsic difficulty [4]. They proposed a bi-convex maximum-likelihood-based solution to the resulting SPARse Factor Analysis (SPARFA) problem. However, the scalability of SPARFA when the number of questions and students significantly increase has not been studied yet.

problems

Some puzzle solving in java and scripting

proj2ir

querying part

rat-finds-cheeze-in-a-maze

This application accepts the position of the rat and cheeze in an auto-generated random maze.It then prints the path rat will follow to get cheeze !

regression-pagerelevancyfeatures

The goal of the project is to: Train a regression model based on query-url pair datasets , then predict the page relevancy labels for new coming queries. Therefore for a given data set with multiple feature vector, A Regression model, that analyses this set of input data and comes up with a function that can accurately predict the output, must first be implemented. The Regression model takes a set of feature vectors as input. Data is then parsed into a machine readable format and imported. The Linear Basis function model employed in supervised learning is them applied to the data set. Linear Basis function model

rtsplib-java

Automatically exported from code.google.com/p/rtsplib-java

samplebatchscript

serialsparesematrixfactorization

smartadsandroid

http://www.cse.buffalo.edu/~lusu/cse721/papers/SmartAds%20Bringing%20Contextual%20Ads%20to%20Mobile%20Apps.pdf

stock-performance

Predicting and computing stock performacne using volatility calculation for Excel based Data

twittertrendsaccumulo

usefulapplescripts

Some apple scripts i wrote that you can also add to your mac and make your life easier

wowclassifier

Please check Frugal classifer repo. Thanks !