Department of Computer Science at University of British Columbia (UBC) . Let's start scrolling and learn more about me.
My name is 'Amin Aghaee'. I was born in 31st December 1992 in Iran. I have got my M.Sc. from Department of Computer Science at University of British Columbia (UBC). My thesis was about using machine learning and data science in geology application. My area of interests are:
ICICS/CS Building 201-2366
Main Mall Vancouver, B.C. V6T 1Z4 Canada
M.Sc. in Computer Science • September 2016 -- January 2019
UBC's Department of Computer Science is one of the top two Computer Science departments in Canada. UBC is ranked as one of the world's top 25 universities for Computer Science.
B.Sc. in Computer Engineering • September 2011--July 2016
Sharif University is the university of choice for the top ranking students attending the nationwide universities entrance exam (Konkoor) which has more than 400,000 participants each year. I admitted to SUT with rank 212 in nationwide university entrance exam.
Diploma in Mathematics and Physics • September 2007--July 2011
Affiliated with the National Organization for the Development of Exceptional Talents (NODET) .
|CPSC 317||Internet Computing||D. Acton||•F2016, S2017|
|DSCI 511||Data Science Programming||Mike Gelbart||•F2017|
|DSCI 575||Advanced Machine Learning||Mike Gelbart||•S2018|
|CPSC 532R||Probabilistic Graphical Models||S. Ravanbakhsh||•S2018|
|DSCI 521||Computing Platforms for Data Science||T. Timbers||•F2018|
|CE 40223||Digital Systems Design||S.B. Sarmadi||•F2015|
|CE 40242||Signals and Systems||Prof. H. Sameti||•S2015|
|CE 40121||Electrical Circuits||Dr. M. Jalili||•F2014, S2015|
|CE 40126||Computer Structure and Languages (Head-TA)||Dr. H. Asadi||•S2015|
|CE 40126||Computer Structure and Languages||Dr. H. Asadi||•F2014|
|CE 40424||Operating Systems||H. Ajorloo||•F2014|
|CE 40212||Logic Design||S.B. Sarmadi||•S2014, F2014|
|CE 40153||Fundamentals of Programming||M. Malekimajd||•F2013|
University of British Columbia• May 2017 - Nov. 2018
Working as a graduate master student in this lab. During my time at LCI/UBC, I could take related courses to my field, work on my thesis, give lecture at Star-AI reading group, and have collaborations with other student in the lab and reading group.
• Suppervisor: Prof. David Poole
Sharif University of Technology• Dec. 2014 - May 2016
Having part-time position as a researcher student during my bachelor studies int this lab. This project was focused on design an active learning method for clustering purposes. More details about this project is available in our publication "Active Distance-Based Clustering using K-medoids".
• Suppervisor: Dr. Mahdieh Soleymani Baghshah
AbstractMinerals exploration is becoming more difficult, particularly because most mineral deposits at the surface of the earth have been found. While there may be a lot of sensing data, there is a shortage of expertise to interpret that data. This thesis aims to bring some of the recent advances in AI to the interpretation of sensing data. Our AI model learns one-dimensional features (lineaments) from two-dimensional data (in particular, magnetics surveys, maps of gravity and digital elevation maps), which surprisingly has not had a great deal of attention (whereas getting two-dimensional or zero-dimensional features is very common). We define a convolutional neural network to predict the probability that a lineament passes through each location on the map. Then, using these probabilities, cluster analysis, and regression models, we develop a post-processing method to predict lineaments. We train and evaluate our model on large real-world datasets in BC and Australia. [PDF ] [UBC Library ]
Title: Software engineer (part-time) • August 2018 - Current
Title: Machine learning developer (MITACS Internship)• September 2017 - August 2018
Minerva provides artificial intelligence software and services to reduce costs and improve success rates in minerals exploration. Artificial intelligence technology makes possible the fast and efficient identification of exploration targets in data sets that are too vast and complex for humans to effectively interpret. Working at Minerva gave me a chance to access real-world geological datasets that I could design, train and improve a computer vision and convolutional neural network model for linear feature extraction (i.e. lineaments) from aerial magnetic images. I have developed my model with Python and Tensorflow library. I also designed a platform for loading datasets, training the model on parallel GPU.
Sharif Wars is real-time strategy games, where players play as their characters and gain experience to level up based on Warcraft game series. The logic base of the program is written in C++ and a graphical layer using Qt framework was added to Attack of the zombies f.Spring 2012
Sharif AI Challenge is an annual group-working contest for challenging abilities in Java programming language and AI concepts which is held by Sharif University of Technology among all universities in Iran.March 2013, 2014, 2015
ZigBee is a specification for a suite of high-level communication protocols used to create personal area networks built from small, low-power digital radios. In this project, we designed a PCB using Altium and integrated chips on it. This image shows one of our Zigbit programmable and portable end node devices.
Team supervisor: Prof. G. MiremadiSummer 2014
"In that darkness the White Walkers came for the first time. They swept through cities and kingdoms, riding their dead horses, hunting with their packs of pale spiders big as hounds. When season 7 of popular TV show Game of Thrones was about to begin, I decided to use and combine image processing techniques for detecting face, eye and skin tone in python, and convert a face into a white walker.July 2017
BeagleBone Black is a low-cost, community-supported development platform for developers and hobbyists. Boot Linux in under 10 seconds and get started on development in less than 5 minutes with just a single USB cable. In this project I implemented a Hardware Security Module on this board and execute a client-server interface based on PKCS #11 standard.
Project supervisor: Dr. S. Bayat-SarmadiSpring 2014
Network on chip is a perfect and scalable solution for communication PEs on a chip. PEs, routers and channels are the elements of the network. In this project we implemented a 4*4 chip network using partially and fully adaptive routing algorithms and packet switching simulated in Verilog-HDL.Fall 2013
The Domain Name System (DNS) is a hierarchical distributed naming system for computers. In this project, a simple DNS system and IP/UDP packets handler was implemented with C++ and simulated on Partov . Partov (Portable and Reliable Tool for Virtualization) is a network simulation and virtualization system, employed as a teaching tool for the computer networks course.Fall 2014
With the advance of artificial intelligence in the last few years, mineral discovery process could become faster and more accurate. The aim of this project is to learn 1-D features (e.g., lineaments) from 2-D aerial images, which surprisingly has not had a great deal of attention. We provide a convolutional neural network to predict existence of lineaments in each location on the map as a probability. Then by using these probabilities, clustering analysis, and regression models, we develop a post-processing method to generate our lineament interpretation. The model is developed with Python/ Tensorflow and the applet is developed with Python/ TK-Inter.Summer 2018
Your work is going to fill a large part of your life, and the only way to be truly satisfied is to do what you believe is great work. And the only way to do great work is to love what you do. If you haven't found it yet, keep looking. Don't settle. As with all matters of the heart, you'll know when you find it.Steve Jobs
It would appear that we have reached the limits of what it is possible to achieve with computer technology, although one should be careful with such statements, as they tend to sound pretty silly in 5 years.John von Neumann
I believe that at the end of the century the use of words and general educated opinion will have altered so much that one will be able to speak of machines thinking without expecting to be contradicted.Alan Turing
Get in touch with me!