Courses and certifications Open Source

Big data

Basic concepts of data science and machine learning

15.000 CZK

Price (without VAT)

Days2
1. 11. 2. 11. 2021
virtual
CZ

Data science, big data, machine learning, deep learning, neural networks, artificial intelligence – we are surrounded with these buzzwords almost every day. In this course you will find out what is really hidden beneath them. We are surrounded by data and we also contribute to its production.

The course covers both business and technical aspects of data science. It introduces the fields and explains how to progress from business problem to solution prototype, to model in production, and how to do it using appropriate tools and technologies. During the course, we also discuss ways of communicating progress and results back to the customer and the importance of model interpretability.

Audience

  • Junior data scientists
  • Data analysts/ engineers who want to get basic knowledge of ML techniques
  • Managers

Goals

  • Find out real meaning of terms Datascience, Machine Learning, Deep Learning and Artificial Intelligence
  • Data scientist every day dutties and workflows
  • How to connect business expertise with machine learning techniques
  • Most common ML methods/ models, its terminology and data preparation

Course guarantor

Tereza Novotná

TERAZA NOVOTNA

Tereza works at DataSentics as a datascientist. After studying financial and actuarial mathematics at the MFF UK, she worked as an actuarial mathematician, later as a data analyst. Currently she is working with big data from their analysis to the position of machine learning automated solutions and production.

Outline

Module 1 - Introduction to Data Science

  • AI vs Machine Learning vs Data Science vs Deep Learning
  • Big data - characteristics and challenges
  • Data Science project lifecycle - from business problem to model in production

LAB I

  • Data types and properties, programming languages

Module 2 – Machine Learning

  • Features and targets, selecting ML technique based on target
  • Implementing machine learning algorithms - languages and
  • Model evaluation
  • Manage model lifecycle - tracing, versioning, archiving (mlflow)
  • Model deployment and testing

LAB II

  • Hands-on model training, comparing and selecting the best one, productionalization

Module 3 - Model's Business Value

  • Visualization of model performance and impact
  • How to communicate results to the client
  • Model interpretability

LAB III

  • Data visualization

LAB IV

  • Course overview hands-on sample data, try to build your own model, interpret its output
  • Communication of results to business

Inquire course

Courses
Submit
* Required field
Cookies help us provide our services. By using our services, you agree to their use.
More information