aakashsinha19

100_Days_of_ML_Code

These are the instructions for "100 Days of ML Code" By Siraj Raval on Youtube

100_Days_of_ML_Code_Challenge

Machine Learning is the most transformative technology of our time. Whether its helping us discover new drugs for major diseases, fighting fraud, generating music, improving supply chain efficiency, the list of applications are truly endless. I am taking up the 100 Days of ML Code as a committment to better my understanding of this powerful tool by dedicating at least 1 hour of my time everyday to studying and/or coding machine learning for 100 days.

Aspectus

Implementation of Image Segmentation and Classification using Python on Tensorflow v0.12 and wrapper Slim, neural net VGG-16s, Scikit Image Library and Inception. The updated version of Aspectus contains custom made sticker batches for Telegram using the output.png file

Cognitive-Sense

This Reporistory contains Study Materials and link for various Online Courses / Certifications. Hope this helps everyone. Cognitive Sense Activated!

FunctionLibrary

A library to learn Algorithms and Data Structures for newbies

Improving-semantic-topic-clustering-for-search-queries-with-word-co-occurrence

Uncovering common themes from a large number of unor- ganized search queries is a primary step to mine insights about aggregated user interests. Common topic model- ing techniques for document modeling often face sparsity problems with search query data as these are much shorter than documents. We present two novel techniques that can discover semantically meaningful topics in search queries: i) word co-occurrence clustering generates topics from words frequently occurring together; ii) weighted bigraph cluster- ing uses URLs from Google search results to induce query similarity and generate topics. We exemplify our proposed methods on a set of Lipton brand as well as make-up & cos- metics queries. A comparison to standard LDA clustering demonstrates the usefulness and improved performance of the two proposed methods. keywords: search queries, topic clustering, word co- occurrence, bipartite graph, co-clustering.

Micro-Codes---Python-Scripts

We often face naive problems in our daily life and wish if there was some way to automate or ease those tasks. Well, here it is! This repository has micro codes written in Python to ease such tasks.

O2---A-Semantic-Search-Engine

O2 leverages Google’s search capabilities to implement a semantic search. The core idea in o2 is to allow a user to find documents based on the Intent within the document. For example a user may want to search for an advanced or a basic document on Java programming. The idea of “advanced” or “basic” is represented as an intent graph. A set of terms that if present in the document, reinforces the fact that the document is indeed “basic” or “advanced” in nature. In addition to intents, o2 uses a vocabulary of terms around which these indexes are to be built. For example, o2 can work with the complete set of topics, a student learns in Java and then act as a semantic search engine for these topics.

scikit-learn

scikit-learn: machine learning in Python

Tweet-Bolt

Implementation of sentiment analysis of tweets using Python and the natural language toolkit NLTK.

aakashsinha19/Improving-semantic-topic-clustering-for-search-queries-with-word-co-occurrence

Uncovering common themes from a large number of unor- ganized search queries is a primary step to mine insights about aggregated user interests. Common topic model- ing techniques for document modeling often face sparsity problems with search query data as these are much shorter than documents. We present two novel techniques that can discover semantically meaningful topics in search queries: i) word co-occurrence clustering generates topics from words frequently occurring together; ii) weighted bigraph cluster- ing uses URLs from Google search results to induce query similarity and generate topics. We exemplify our proposed methods on a set of Lipton brand as well as make-up & cos- metics queries. A comparison to standard LDA clustering demonstrates the usefulness and improved performance of the two proposed methods. keywords: search queries, topic clustering, word co- occurrence, bipartite graph, co-clustering.

aakashsinha19/O2---A-Semantic-Search-Engine

O2 leverages Google’s search capabilities to implement a semantic search. The core idea in o2 is to allow a user to find documents based on the Intent within the document. For example a user may want to search for an advanced or a basic document on Java programming. The idea of “advanced” or “basic” is represented as an intent graph. A set of terms that if present in the document, reinforces the fact that the document is indeed “basic” or “advanced” in nature. In addition to intents, o2 uses a vocabulary of terms around which these indexes are to be built. For example, o2 can work with the complete set of topics, a student learns in Java and then act as a semantic search engine for these topics.

aakashsinha19/100_Days_of_ML_Code

These are the instructions for "100 Days of ML Code" By Siraj Raval on Youtube

aakashsinha19/100_Days_of_ML_Code_Challenge

Machine Learning is the most transformative technology of our time. Whether its helping us discover new drugs for major diseases, fighting fraud, generating music, improving supply chain efficiency, the list of applications are truly endless. I am taking up the 100 Days of ML Code as a committment to better my understanding of this powerful tool by dedicating at least 1 hour of my time everyday to studying and/or coding machine learning for 100 days.

aakashsinha19/Aspectus

Implementation of Image Segmentation and Classification using Python on Tensorflow v0.12 and wrapper Slim, neural net VGG-16s, Scikit Image Library and Inception. The updated version of Aspectus contains custom made sticker batches for Telegram using the output.png file

aakashsinha19/Cognitive-Sense

This Reporistory contains Study Materials and link for various Online Courses / Certifications. Hope this helps everyone. Cognitive Sense Activated!

aakashsinha19/FunctionLibrary

A library to learn Algorithms and Data Structures for newbies

aakashsinha19/Micro-Codes---Python-Scripts

We often face naive problems in our daily life and wish if there was some way to automate or ease those tasks. Well, here it is! This repository has micro codes written in Python to ease such tasks.

aakashsinha19/scikit-learn

scikit-learn: machine learning in Python

aakashsinha19/Tweet-Bolt

Implementation of sentiment analysis of tweets using Python and the natural language toolkit NLTK.

aakashsinha19/Cpp-Programming

aakashsinha19/Crawler

aakashsinha19/crfasrnn

This repository contains the source code for the semantic image segmentation method described in the ICCV 2015 paper: Conditional Random Fields as Recurrent Neural Networks. http://crfasrnn.torr.vision/

aakashsinha19/deep-learning-coursera

Deep Learning Specialization by Andrew Ng on Coursera.

aakashsinha19/Fast-Personalized-PageRank-on-MapReduce

We will design a fast MapReduce algorithm for Monte Carlo approximation of personalized PageRank vectors of all the nodes in a graph. The basic idea is very efficiently doing single random walks of a given length starting at each node in the graph. More precisely, we design a MapReduce algorithm, which given a graph G and a length λ, outputs a single random walk of length λ starting at each node in G. We will show that the number of MapReduce iterations used by our algorithm is optimal among a broad family of algorithms for the problem, and its I/O efficiency is much better than the existing candidates. We will then show how we can use this algorithm to very efficiently approximate all the personalized PageRank vectors. Our empirical evaluation on real-life graph data and in production MapReduce environment shows that our algorithm is significantly more efficient than all the existing algorithms in the MapReduce setting.

aakashsinha19/Flight-Delay-Prediction-Using-Scalable-Data-Mining

To Develop accurate prediction models (like Naiive Bayes, Logistic Regression or Decision Tress) for flight delays using a generic database to overcome the difficulties faced by passenger travelling in huge numbers daily and come up with an optimized result.

aakashsinha19/Food-Recognition-Web-App-Shazam-for-Food-

aakashsinha19/galaxy-image-classifier-tensorflow

Classify whether an image is of a Spiral or an Elliptical Galaxy using Transfer Learning (Tensorflow)

aakashsinha19/hub

A library for transfer learning by reusing parts of TensorFlow models.

aakashsinha19/Java-Programming

aakashsinha19/Micro-Codes

Short Codes for automating some boring stuff using Python :octocat: :beer: :zzz:

aakashsinha19/ML_Sessions_Code

ML Sessions Code Repository

aakashsinha19/Networking

aakashsinha19/Programming-Tools

aakashsinha19/SHARQ

Implementing SHARQ protocols in openLTE and study performance variation with Maximum HARQ rounds.

aakashsinha19/Shirley---A-Generic-Chat-Bot

A generic chat bot made using Watson Conversation API.

aakashsinha19/SOC-Summer-of-Code-

Coding Practice for Summer 2017

aakashsinha19/tensorflow

Computation using data flow graphs for scalable machine learning

aakashsinha19/tf-image-segmentation

Image Segmentation framework based on Tensorflow and TF-Slim library

aakashsinha19/transfer-learning-image-classifier

Build an image classifier using transfer learning