About

Hello there!

My name is Elaine. I am a student at the University of Toronto, in the Master of Science in Applied Computing program. I am interested in Artificial Intelligence, specifically Machine Learning and Data Mining. Other areas of interest to me are human-computer interaction (HCI) and software engineering.

Programming Languages:
Python, Java, Ruby, C, C++

Back-end Web Technology:
Ruby on Rails, Django, Node.js

Front-end Web Technology:
React, Handlebars, jQuery, Backbone.js, Sasss, Bootstrap

ML/DS Libraries:
Theano, Chainer, Keras, Numpy, Scipy

Email: elainemalit@cs.toronto.edu
LinkedIn: Mary Elaine Ramos Malit

Academics

MScAC (Sep 2016 - present)

Mood-Based Image to Music Synthesis

CSC2541: Differentiable Inference and Generative Models

The goal of this project is to generate music that evokes the same mood as an image. A pre-trained convolutional neural network extract the features of an image, and is then used to condition the first timestep of a recurrent neural network. The RNN is trained to produce music.

Project Paper

Analytic Visualization of Book Recommendations

CSC2524: Information Visualization

This project tries to tackle the problem where book recommendations from black-box systems usually appear in lists that don't facilitate item comparisons. Books are high-dimensional entities that can be compared on a number of different metrics like popularity and genres. This visualization provides 3 different views that allow users to explore the recommendation space through multiple perspectives.

Project Paper
Proof of Concept

Research Internship (May 2013 - Aug 2013)

SerpenTI: Flexible Analytics of Users, Boards and Domains for Pinterest

Database Lab

The aim of this research project was to provide an analytics platform for Pinterest. Given a query, we want to provide a list of Pinterest users and boards that are good sources for that query. My contribution to the research project was the front-end visualization of the analytics.

Research Paper

Honours BSc (Sep 2010 - May 2014)

Specialist in Computer Science
Minor in English

Classification of Tweets

CSC401: Introduction to Natural Language Computing

The goal of this course assignment is to utilize NLP techniques in processing tweets so they can be classified into categories. Developed in Python, features such as number of adverbs, average word length, and frequency of punctuation were calculated. Then the WEKA machine-learning module was used to classify the tweets according to user and/or genre (ex. pop, news, science, etc.)

Classification of Handwritten Digits

CSC411: Introduction to Machine Learning and Data Mining

I implemented three classifiers (k-nearest neighbours, logistic regression and naive Bayes) to compare their performance in classifying images of handwritten 2s and 3s.

For more information about my Academic background and relevant projects, please download a copy of my CV.

Industry

Front-End Software Engineer (May 2014 - Aug 2016)

BiblioCommons

Responsive Explore Pages

The libraries' explore pages help patrons find items of interest. Unlike the query-driven search pages, the explore pages facilitate a more serendipitous experience by exposing patrons to new items, recently reviewed items, award-winning items, best-selling items, or items recommended or curated by library staff. The goal of this project was to bring BiblioCommons' explore pages to the 21st century by updating the UX and making the pages responsive. See Live

Responsive User Pages

To bring patrons a more personalized experience using the online library catalogue, BiblioCommons completely refactored the user dashboard page. Along with providing an overview of the user's borrowing status, the user dashboard page now incorporates other BiblioCommons features like item recommendations and activity feeds. One of BiblioCommons' goals is to leverage social networking to help cultivate the library's online community. To support this goal, we developed a series of brand new features like user profiles, user activity feeds, newsfeeds and notification feeds. These pages better demonstrate a user's role and contributions in the online community. See Live

Responsive User Lists

User lists are one of the most important feautures provided by BiblioCommons. Users are allowed to create their own custom lists, grouping together items that share commonalities. Lists allow other users to find items that may be of interest to them. This project refactored the list page to make it responsive, enabling users to browse lists on mobile. This page enables users to place items on hold, to check out digital items, and to add items to their shelves. See Live

Suggested Purchases Canned Responses

Many libraries have a Suggest for Purchase feature, where patrons can request for an item to be purchased so that they can borrow it. Canned responses are reusable replies that the library admins can use to reply to suggestions. This page allows library admins to create, update, view and delete their canned responses. Admins only

Summer Sites Badges

The Summer Reading Sites encouraged people to read in the summer. One way we helped libraries with their summer reading program was by awarding participants virtual badges. Participants can earn badges for achieving a certain task like completing their summer reading challenges, contributing online ratings and reviews, or accomplishing custom tasks set by the libraries. Library admins could create custom badges for particular tasks. We also allowed them to create super badges - a badge to be awarded to a user who managed to earn a set of other badges. Deprecated

Hobby

I like to read, write and draw in my free time. I really love Fantasy books in particular! Here's my Goodreads page. You can view my Wordpress blog here and my drawings here. I'm happy to announce that one of my short stories will be published this year in the annual Philippine Speculative Fiction anthology. And here are a few of my artworks and some of my favourite books.

Disclaimer
Icons made by Madebyoliver from www.flaticon.com is licensed by CC 3.0 BY
Icons made by Freepik from www.flaticon.com is licensed by CC 3.0 BY
Icons made by Dave Gandy from www.flaticon.com is licensed by CC 3.0 BY
Icons made by Freepik from www.flaticon.com is licensed by CC 3.0 BY
Icons made by Google from www.flaticon.com is licensed by CC 3.0 BY