RESERVE MY SPOT
Alex Dainiak was born in Moscow in 1985. He had his first encounter with programming in 1998 while studying a Pascal circle and discovered he loved it. After working for some time as a programmer, he turned to mathematics. Alex Dainiak now considers himself a professional tutor and applied mathematician rather than a programmer. Nevertheless, he still produces a reasonable amount of code from time to time and takes part in personal and collective software development projects.
Research/Academic Interests:
Graph Theory, Combinatorics, Data Visualisation, Discrete Optimisation
The main goal of the course is to empower learners with knowledge about the optimization algorithms that essentially take the most computation time in the fitting and computation of the machine learning model. Thus, the learner can make informed decisions while choosing the ML model class, the fitting strategy and even the manual implementation.
SKILLS:
- Algorithms
- Computer Science
- Machine Learning
- Discrete Mathematics
- C++
- Research
- Python
- Data Analysis
- Natural Language Processing
DATE: 27 Jan - 14 Feb, 2020
DURATION: 3 Week
LECTURES: 3 Hours per day
LANGUAGE: English
LOCATION: Barcelona, Harbour.Space Campus
COURSE TYPE: Offline
WHAT YOU WILL LEARN
ABOUT ALEX
After you define a model in machine learning, you tune the model to the data at hand. Mathematically it usually just boils down to optimizing the fitness function of the model. Naturally, various mathematical optimization methods become an important part in your data scientist’s toolbox as soon as you start working with lots of data and complex models. Even if you do not implement optimization algorithms in your daily analyst’s routine, it is a good idea to be well informed of what goes under the hood when you fit your model, so that you make an informed decision on the parameters of the optimization algorithms and the choice of the algorithm itself. As a bonus, applications of mathematical optimization go well beyond machine learning, so the course material may help you in a computer science career in general.
ALEX DAINIAK
DATE: 27 Jan – 14 Feb, 2020
DURATION: 3 Weeks
LECTURES: 3 Hours per day
LANGUAGE: English
LOCATION: Barcelona, Harbour.Space Campus
COURSE TYPE: Offline
All rights reserved. 2017
COURSE OUTLINESession 1
Course outline. Recap of fundamental mathematical concepts: derivatives, convexity, matrix computations.
Session 2
ML models: linear regression, logistic regression, generalized linear models. Regularization. SVM model. Neural net model.
Session 3
ML models continued: optimization framework.
Session 4
Implementing regularization in regression and matrix decompositions.
OPTIMIZATION METHODS IN MACHINE LEARNING
OPTIMIZATION METHODS IN MACHINE LEARNING
BIBLIOGRAPHY
Foundations of Data Science by Avrim Blum, John Hopcroft, Ravi Kannan. (Cambridge University Press. 2020)
Understanding Machine Learning: From Theory to Algorithms by S. Shalev-Shwartz, S. Ben-David. (Cambridge University Press. 2014)
Harbour.Space is a university created by entrepreneurs for entrepreneurs. We focus on meeting the demands of the future, while traditional education providers are too often stuck in the past.
We’re one of the only European institutions completely dedicated to technology, design and entrepreneurship, and our interdisciplinary courses are taught by some of today’s leading professionals. Our aim is not only to equip students with the knowledge to take on the real world, but to nurture, create and shape tomorrow’s tech superstars.
HARBOUR.SPACE HARBOUR.SPACE UNIVERSITY
