Program

In this course you will learn how to program in R and how to use R for effective data analysis with a  particular focus on using R for software development in a data science setting. You will learn how to leverage  packages necessary for a statistical programming and understand generic programming language concepts to use in a high-level statistical language. The course covers basic R language fundamentals, key concepts, and practical issues in statistical computing which includes programming in R, reading data into R, accessing R packages, writing R functions, debugging, profiling R code, and organizing and commenting R code. Course will provide hands on working examples.

Tools - R/RStudio

 Necessary skills to participate in the course - Analytical thinking, desire to learn

Instructor

Dr. Margarit Khachatryan

US, Founder and CEO of MagAnalytics

This course aims to provide the basics of programming in Python with a special focus on data analysis. The participants will learn how to leverage Pandas for reading, manipulating and summarizing data, how to visualize results using Matplotlib and Seaborn. Numpy and Scipy  packages will be introduced for scientific computing in Python.

Instructor

Dr. Hrant Davtyan

Armenia, Assistant Professor of Data Analytics, AUA

Inferential statistics allows to draw conclusions from data that might not be obvious. This course focuses on enhancing participants’ ability to develop statistical hypotheses and use both parametric and non-parametric hypothesis testing tools like t-tests, Chi-square and other tests to validate proposed claims.

Tools - R

Necessary skills to participate in the course - Basic Statistics (measures of central tendency and variation). Basic programming skills in R

Instructor

Vahe Movsisyan

Armenia, Central Bank of Armenia,  AUA, Co-founder of Datamotus LLC

Nowadays, large amount of data is available everywhere. Therefore, it is very important to analyze this data in order to extract some useful information and to develop an algorithm based on this analysis. This can be achieved through data mining and machine learning. Machine learning is an integral part of artificial intelligence, which is used to design algorithms based on the data trends and historical relationships between data.
In this course equips you to implement machine learning algorithm using python, through implementation of k-nearest neighbors, naive Bayes, support vector machine, neural network, and others, you will explorer a variety of machine learning algorithm, then you can select the best model, considering key principles of how to implement those models effectively.

Instructor 

Mr. Artin Zomorodian

Iran, Faculty Member, Azad University

In this course, attendees will be provided with an overview perspective on location-based technologies with a focus on urban applications. From human mobility models and
theory to neighborhood detection and finding an appropriate location for placing a shop or amenity attendees will be introduced to the mechanics and building blocks of a number of research works with a strong application orientation. Historically important theoretical concepts in the area will be covered that include Central Place Theory and Reilly’s law of retail gravitation. Next, the spotlight will be put on newer advancements in the area of the so-call gig economy, introducing services like Uber and Airbnb, highlighting opportunities for research using corresponding transport and hospitality datasets.

Tools - Python, Mapbox

Instructor 

Dr. Anastasios Noulas

USA, Assistant Professor and Faculty Fellow, Center of Data Science, New York University

The intent of the course is to present an introduction to Natural Language Processing, the study of computing systems that can process, understand, and analyze human language. The primary focus of the course will be on understanding various NLP tasks, such as information extraction and information retrieval, discussing algorithms for effectively solving these problems, as well as methods for evaluating their performance.

Tools - Python, Perl

Necessary skills to participate in the course - Basic programming skills, as well as reasonable knowledge of mathematics and statistics.

Instructor 

Dr. Lana Yeganova

USA, Scientist at NIH

This course will introduce the students to the world of Computer Vision, starting with a brief history of the field all the way to the recent advances of image processing. We will be using the famous open source library OpenCV to load and manipulate images.

Tools - OpenCV

Necessary skills to participate in the course - Basic programming skills (preferably in Python)

Instructor 

Mr. Christophe Zoghbi

Lebanon, Computer Vision & Machine Learning Consultant

In this course we will cover the basics of neural networks. We will study how the neural networks learn (backpropagation), how they can be adapted to handle 2D image data (convolutional networks) and sequential data (recurrent neural networks).

Tools - Jupyter notebooks, Keras

Necessary skills to participate in the course - Python programming, multivariate calculus

Instructor 

Dr. Hrant Khachatrian

Armenia, YerevaNN, Director

The course will provide a comprehensive introduction to time series  visualization, modeling and forecasting. It will teach the R language functions for time series analysis. Main topics include data decompositions, classical forecasting models such as exponential smoothing and ARIMA, hypothesis testing for trend and seasonality detection, algorithms for period detection. The main point of discussions should be clarifying the difference between deterministic and stochastic characteristics of time series.

Tools - Powerpoint, Rstudio

Necessary skills to participate in the course - R language, calculus, statistics, probability

Instructor 

Dr. Arnak Poghosyan

Armenia, VMware

Deep Learning adds a huge boost to the field of Computer Vision. In this course, we will introduce a special type of Neural Networks called Convolutional Neural Network, that are used to extract features from images. We will used these networks to build image classification and object detection models.

Tools - Jupyter notebooks (or Google Colab), Tensorflow/Keras

Necessary skills to participate in the course - Basic knowledge of how Neural Networks work, basic programming background

Instructor 

Mr. Christophe Zoghbi

Lebanon, Computer Vision & Machine Learning Consultant

An enormously large series of complex and chaotic events have shaped the genomes of eukaryotes, prokaryotes and viruses. This course will address cutting edge approaches for the computational investigation of these events, with an eye toward developments in translational systems biology. The course will present the fundamentals of genome analysis and data management focusing on data search and retrieval, similarity searches, genome assembly and annotation, metagenomics and comparative genomics.

Tools - NCBI online resources (Entrez, BLAST, SRA), Python

Necessary skills to participate in the course - Basic concepts of Molecular Biology

Instructor Profile

Dr. Tatiana Tatusova

USA, Senior Scientist, NCBI/NLM/NIH

The course will cover the general ML approaches used for recommendation systems (memory based and model based, explicit and implicit user feedback, etc). It will cover different algorithms, from very basic to more advanced - Matrix Factorization, Factorization machines, Neural Networks based, Hybrid recommenders, etc.

Instructor

Dr. Arsen Yeghiazaryan

Webb Fontaine, Machine Learning Specialist

During the lecture I'm more than excited to walk participants through basics and definitions of survival analysis. We will walk step by step by the most crucial parts of the data analysis procedure in the scenario of time-dependent data and areas of censored information. There will be a place to learn diagnostic plots used in the formulation and verification of cox proportional hazards model, which is the most know procedure applied to churn analytics. If there is a time, we can consider model for multi-state nature of the survival analysis.

Tools - R, RStudio

Necessary skills to participate in the course - Basic idea of R usage and basic knowledge about linear models (like linear regression)

Instructor 

Mr. Marcin Kosinski

Poland, Statistician at Gradient Metrics LLC

During the two days, the students should be able to write a web scraping code in R (using packages (I) RSelenium, (II) httr and XML or (III) rvest).

The collected data from web would be processed using dplyr package. The students will learn how to use ggmap package to enrich their data with geographical information and create cool maps. Besides, we will use ggplot2 and the basic graphics for the graphical exploratory data analysis.

During the course, I will use the following websites for scraping:
1. www.immoscout24.de – P1 GOAL: Figure out the rent prices in German counties. Find the variables, which could explain the higher price level on the flat rent market (For example, we could investigate the rents in Berlin area).
2. www.betexplorer.com – P2 GOAL: Figure out if there is a possibility for risk-less profit by allocation of the bet between different bookies for the same game.

After accomplishing this course, students should be able to write their very own R scraper to collect data and answer the research question they are interested in. Further projects with an ongoing remote supervision is possible (e.g. www.sas.am, www. parliament.am, www.rate.am, www.list.am etc).

Tools - Slides/tasks. We are going to code a lot together!

Necessary skills to participate in the course  - Solid Background in R (dplyr, stringr), HTML and Fundamentals of Econometrics

Instructor 

Dr. Andranik Stepanyan

Germany, Senior Data Analytics Consultant

Large amounts of heterogeneous data are becoming available in medicine and healthcare, from electronic health records to genomic data, and data collected by various wearable devices. The scale, diversity and complexity of these datasets present serious challenge in analyses and subsequent practical applications. In this course, you will learn about successful case studies with state-of-the-art applications of big data and artificial intelligence in healthcare. You will get familiar with some of the different types of data and machine learning methods involved in data science for healthcare and will have a hands-on experience of working with such data.

Tools - Jupyter Notebook, Python, scikit-learn

Necessary skills to participate in the course  - Python

Instructor 

Dr. Harutyun Shahumyan

Ireland, Visiting Research Fellow at University College Dublin and Senior Data Scientist at United Health Group

In this course you learn how to build up your data science platform with AWS. You will learn how to control costs and which services help you to prepare your data for later application of ML application.

Tools - AWS, PyCharm, VIM,

Necessary skills to participate in the course  - Linux, Python and SQL basics, a general understanding of hardware and networks

Instructor 

Mr. Stephen Papp

Austria, Lecturer and Entrepreneur

The first part of the course aims to familiarize the participants with Facebook's FastText algorithm. In the second part we will implement the algorithm in tensorflow.

Tools - Laptop with Python and Tensorflow pre-installed

Necessary skills - Python, Tensorflow, familiarity with text classification will help

Instructor

Mr. Sipan Muradyan

Machine Learning Specialist