Machine Learning (CS-455) Spring 2017 (https://sites.google.com/site/nomanmachinelearningclass/)

► Course Content:

1. Introduction to Machine Learning.
2. Concepts Space and K-NN + Over-fitting and Under-fitting + Cross validation).
3. Decision Trees and Rule pruning
4. Naive Bayes and Bayesian Belief Networks
5. Linear Regression with Multiple Variables
6. Logistic Regression
7. Regularization
8. Neural Networks and Back propagation Algorithm
9. Advice for… Show more

Machine Learning (CS-455) Spring 2017 (https://sites.google.com/site/nomanmachinelearningclass/)

► Course Content:

1. Introduction to Machine Learning.
2. Concepts Space and K-NN + Over-fitting and Under-fitting + Cross validation).
3. Decision Trees and Rule pruning
4. Naive Bayes and Bayesian Belief Networks
5. Linear Regression with Multiple Variables
6. Logistic Regression
7. Regularization
8. Neural Networks and Back propagation Algorithm
9. Advice for applying machine learning
10. SVM and Softmax loss Show less

Abstract Governments these days are demanding better Smart City technologies in order to connect with citizens and understand their demands. For such governments, much needed information exists on social media where members belonging to diverse groups share different interests, post statuses, review and comment on various topics. Aspect extraction from this data can provide a thorough understanding of citizens’ behaviors and choices. Also, categorization of these aspects can better summarize… Show more

Abstract Governments these days are demanding better Smart City technologies in order to connect with citizens and understand their demands. For such governments, much needed information exists on social media where members belonging to diverse groups share different interests, post statuses, review and comment on various topics. Aspect extraction from this data can provide a thorough understanding of citizens’ behaviors and choices. Also, categorization of these aspects can better summarize societal concerns regarding political, economic, religious and social issues. Aspect category detection (ACD) from people reviews is one of the major tasks of aspect-based sentiment analysis (ABSA). The success of ABSA is mainly defined by the inexpensive and accurate machine-processable representation of the raw input sentences. Previous approaches rely on cumbersome feature extraction procedures from sentences, which adds its own complexity and inaccuracy in performing ACD tasks. In this paper, we propose an inexpensive and simple method to obtain the most suitable representation of a sentence-vector through different algebraic combinations of a sentence’s word vectors, which will act as an input to any machine learning classifier. We have tested our technique on the restaurant review data provided in SemEval-2015 and SemEval-2016. SemEval is a series of global challenges to evaluate the effectiveness of disambiguation of word sense. Our results showed the highest F1-scores of 76.40% in SemEval-2016 Task 5, and 94.99% in SemEval-2015 Task 12. Show less

Classifier to detect spam and not spam messages using SVM and Naive Bayes

This is the software for Aspect Category Detection in Aspect Based Sentiment Analysis task.

Techniques and Software:
Word2vec, Deep Neural Networks, Multi-label classification, Text Mining

Neural-Networks for Digit Recognition

Built a three-layer neural network to recognize the digits. For this purpose we will be using the famous MNIST dataset.

Jal Bujh is our first product aimed at making a 60 year old technology iOT enabled. An environment polluting, natural gas (Sui gas) wasting water heater can be made into a intelligent consumer appliance with by coupling Jal Bujh to it saving households upto 50% on their water heating bill whiel savings tens of millions of dollars a month if Jal Bujh is installed on every single water heater in our first target market. For individuals, the devices pays back its price in less than one winter… Show more

Jal Bujh is our first product aimed at making a 60 year old technology iOT enabled. An environment polluting, natural gas (Sui gas) wasting water heater can be made into a intelligent consumer appliance with by coupling Jal Bujh to it saving households upto 50% on their water heating bill whiel savings tens of millions of dollars a month if Jal Bujh is installed on every single water heater in our first target market. For individuals, the devices pays back its price in less than one winter season and while continued savings for many many years. Show less

FMG App is a Meta application that can be customized and sold to financial services firms serving private clients. The app displays news, articles and financial planning tools for individual users who are clients of a particular financial services firm. The app is customized for each financial services firm that buys it and the customized app is submitted to Google under the firm’s name. Each application is compiled and builds through automated android build system for saving time for… Show more

FMG App is a Meta application that can be customized and sold to financial services firms serving private clients. The app displays news, articles and financial planning tools for individual users who are clients of a particular financial services firm. The app is customized for each financial services firm that buys it and the customized app is submitted to Google under the firm’s name. Each application is compiled and builds through automated android build system for saving time for compilation. The firm selects the content it wants the app to display by configuring it in the content management system housed on a server. The user interface is configured dynamically by pushing icons, layout information and new content at run time. A caching mechanism keeps the Meta and content in sync with the server without the need to refresh it on every application launch. Show less

Android App for English Handwritten Text Recognition

This is the software for Optical character recognition of Handwritten and Printed English Text

Won best project idea award in Software Competition at GIFT University