Abien Fred Agarap

Reading time ~17 minutes

Curriculum Vitae [pdf]


Computer Scientist and Mathematician focusing on Theoretical Artificial Intelligence (AI) and Machine Learning. He works as a part-time AI Researcher at Senti Techlabs, Inc. and as a part-time AI Consultant at AI Pilipinas. His researcrh interests are the Foundations of Machine Learning and Deep Learning, the Intersection of Machine Learning and Game Theory, and Numerical Analysis theories and applications. He was a part of the Philippine Team to the Intel International Science and Engineering Fair (Intel ISEF) 2013 in Phoenix, Arizona, USA.


Experience

AI Consultant (April 2018 - present)
AI Pilipinas
Makati, Philippines

AI Researcher (April 2018 - present)
Senti Techlabs, Inc.
Makati, Philippines

AI Developer Apprentice (December 2017 - March 2018)
Senti Techlabs, Inc.
Makati, Philippines


Education

Bachelor of Science in Computer Science, (November 2013 - March 2018)
Graduating Cumulative GPA of 1.72/1.00 (over-all); 1.65/1.00 (major)
Adamson University
Manila, Philippines

Bachelor of Science in Computer Science, (July 2013 - October 2013)
Mapua Institute of Technology
Makati, Philippines

Nabuslot National High School (June 2009 - March 2013)
Special Science Class. Finishing GPA of 93.101/100
Most Outstanding Young Researcher of Orienta Mindoro (2012 - 2013)
Oriental Mindoro, Philippines


Selected Awards and Honors

An offer of MSc scholarship (October 2017)
Hult International Business School
San Francisco, CA, USA

2nd Runner Up (December 2015)
Java Code Fest
Far Eastern University (FEU) - Institute of Technology

1st Runner Up (September 2015)
2nd Intercollegiate Java Programming Contest
Technological Institute of the Philippines (TIP) - Manila

Finalist (May 2013)
Intel International Science and Engineering Fair
Society for Science & the Public

Intel Excellence in Computer Science (February 2013)
Department of Education, National Science and Technology Fair

Grand Award, Physical Science, Individual (December 2012)
Department of Education, National Science and Technology Fair

1st Place (September 2012)
2012 - 2013 Regional Science Festival
Department of Education - MIMAROPA Region

Runner Up (October 2011)
DOST Regional Invention Contest and Exhibits (RICE) 2011
Department of Science & Technology - MIMAROPA Region

1st Place (September 2011)
2011-2012 Regional Science Festival
Department of Education - MIMAROPA Region

2nd Place (September 2010)
2010-2011 Regional Science Festival
Department of Education - MIMAROPA Region


Projects

Deep Learning using Rectified Linear Units (ReLU)
[code][paper]
March 2018. An introduction of deep learning approach where the last layer is ReLU.

Statistical Analysis on E-Commerce Reviews, with Sentiment Classification using Bidirectional Recurrent Neural Network (RNN)
[code][paper]
February 2018 - March 2018. Co-authored with Paul M. Grafilon, PhD. Univariate and multivariate analysis on clothing e-commerce reviews, with text classification on customer recommendation and review sentiment.

Towards Building an Intelligent Anti-Malware System: A Deep Learning Approach using Support Vector Machine for Malware Classification
[code][paper]
November 2017 - December 2017. Co-authored with Francis John Hill Pepito. A pre-cursor towards the engineering of an intelligent anti-malware system employing a deep learning approach for the detection of previously-unknown malware.

An Architecture Combining Convolutional Neural Network (CNN) and Support Vector Machine (SVM) for Image Classification
[code][paper]
November 2017 - December 2017. An implementation of a 2-Convolutional Layer with Max Pooling CNN that uses an SVM classifier.

On Breast Cancer Detection: An Application of Machine Learning Algorithms on the Wisconsin Diagnostic Dataset
[code][paper]
A submitted paper to the 2nd International Conference on Machine Learning and Soft Computing
September 2017 - November 2017. Implementation of six machine learning (ML) algorithms: GRU-SVM, Linear Regression, Multilayer Perceptron (MLP), Nearest Neighbor (NN) search, Softmax Regression, and Support Vector Machine (SVM) on the Wisconsin Diagnostic Breast Cancer (WDBC) dataset, measures their classification test accuracy and their sensitivity and specificity values.

A Neural Network Architecture Combining Gated Recurrent Unit (GRU) and Support Vector Machine (SVM) for Intrusion Detection
[code][paper]
An accepted paper at the 10th International Conference on Machine Learning and Computing
April 2017 - October 2017. An implementation of the GRU-SVM model for intrusion detection, written using Python.

On Breast Cancer Detection: An Application of Support Vector Machine (SVM) Algorithm
[code][paper]
October 2017. An implementation of the L2-SVM algorithm, a part of my research on application of machine learning algorithms for breast cancer detection on the Wisconsin diagnostic dataset.

On Breast Cancer Detection: An Application of Multilayer Perceptron (MLP) Algorithm
[code][paper]
October 2017. An implementation of the MLP algorithm, a part of my research on application of machine learning algorithms for breast cancer detection on the Wisconsin diagnostic dataset.

Mathematics for Machine Learning
[notebook]
September 2017. A Jupyter Notebook that consists of review notes for the pre-requisite Mathematics for Machine Learning.

GRU-SVM for Fashion-MNIST Classification
[code][benchmark data]
August 2017. An application of my proposed GRU-SVM model for image classification on the Fashion-MNIST dataset by Zalando Research.

harvester
[code]
November 2015. A project for educational purposes only. An ionic framework app that uses firebase to store the ‘harvested’ Facebook account credentials, through phishing.

TransCopy
[code]
August 2015. A Microsoft Windows native app that copies single or multiple files to one or more connected USB storage devices.

REAVIS (Revolutionary Antivirus) - A Personal Computer System Ultimate Virus Prevention Program
[installer][paper][media coverage]
January 2012 - May 2013. REAVIS is a computer program designed to prevent computer system infections, and improve computer security and stability.

JAM Folder Protector
[code]
September 2012. A Microsoft Windows native app that provides personal folder security using Microsoft’s NTFS technology.