Machine Learning in practice

- Beginners level -

Register and start learning!
4 month course - applied machine learning
Theme
What is machine learning?
Machine learning is the study of computer algorithms that are automatically improved through experience and the use of data. It is considered part of artificial intelligence. Machine learning algorithms build a model based on a data sample, known as "training data". Such a model makes decisions or predictions, for situations for which it is not explicitly programmed.
Structure
Components of machine learning
Machine learning is based on 2 components, model and data.
The model itself, no matter how efficient and "smart" it is, without quality data, will not work efficiently.
We often emphasize the analogy between the model-data concept and the mind-experience analogy. No matter how smart we are, without experience, it is difficult for us to make the right decisions in critical situations. Also, no matter how experienced we are, if we are less smart, it is debatable what decisions we will make.
When we train models with the data we have, we say that the model learns. We learn from experience, and if we are smart, we learn quickly and do not repeat the same mistakes, just like our models of machine learning do.
This course will cover both the concept of the model and also the concept of the data and it's quality.
The aim of the course is to train you to create basic models of machine learning and partial and deep learning. You can use this knowledge to solve a large number of practical problems that are difficult to solve with traditional programming.
Vladimir Obradović
Course instructor
Vladimir Obradović
Course instructor
Vladimir Obradović, founder of IAMAI academy, translates his many years of engineering experience gained in the IT industry, working for leading investment banks, government organizations, startups and mainstream IT companies, into plain language understandable to beginners and students without programming experience. He bases his lectures on modern principles of learning psychology.
Vladimir Obradović
Course instructor
Vladimir Obradović, founder of IAMAI academy, translates his many years of engineering experience gained in the IT industry, working for leading investment banks, government organizations, startups and mainstream IT companies, into plain language understandable to beginners and students without programming experience. He bases his lectures on modern principles of learning psychology.
At the following link you can see the products and solutions that I personally developed. Portfolio
Vladimir Obradović
Course instructor
During the course, we will cover standard Python programming language libraries in the field of machine learning. This knowledge and experience in your CV highlights you as a serious candidate when applying to the vast majority of jobs (professors, teachers, finance, marketing, business analysts, system administrators, software support, etc.).
Pitanje:
After this course, as an absolute beginner, can I get a job at Google, Microsoft or Tesla?
Odgovor:
Unfortunately no.
This course is a necessary but not a sufficient condition for a change in your career. The course provides you with a solid foundation for development in this area. And with further work, whether through independent learning or through advanced courses in this field, you open the possibility for professional work in the field of machine learning.

At the end of the course, participants receive a certificate of completion of the course with a specification of the topics they covered in the course.
Sign up and learn!
Important notes
Register on time
  • 1
    Contact and questions
    Additional information (WhatsApp): +31 61 272 9661, working days from 07:30 to 19:30 and saturday from 09:00 to 15:00
  • 2
    Additonal material
    Recorded live lessons
  • 3
    Price
    Price: 320 Euro per month. Payments in 4 installments.
  • 4
    Lecture times
    Tuesday, Friday from 20:00 till 22:00
  • 5
    Beginning
    To be anounced
  • 6
    Total lessons
    32 lessons, 1 lesson 2 hours
  • 7
    Structure of a lesson
    1.5 h lesson, 30min independent or work in group
  • 8
    Course plan
    32 lessons in period of 4 months, 2 times per week.
  • 9
    Applications
    After registrations, you will receive payment details and a link to a first lesson.
Course program
We will cover following chapters
1
Introduction

Fundamentals of machine learning and artificial intelligence


  1. Practical examples of artificial intelligence
  2. What is AI, history, classification
  3. Machine Learning explained
  4. Deep Learning explained

The aim of this chapter is to learn what machine learning is and what artificial intelligence is in general and their significance. To understand what problems we solve using machine learning algorithms.

2
Python
Python language basics

  1. What is Python, history
  2. How Python works, Anaconda environment installation
  3. Sintax, data types, how to communicate with world
  4. Loops
  5. Conditions and decisions
  6. Working with files
  7. Pandas (Python Data Analysis Library)
  8. Pandas - examples
  9. Python and data visualization
The goal of this chapter is to learn how we can install the Python programming environment.
At the same time, this area is both a short repetition and an accelerated course of Python.
3
Google Colab

How to use Google cloud with powerful servers to train large models


  1. What is Google Colab, basic options, disk mounting

The goal of this chapter is to learn how to work with the Google Colab infrastructure.

4
Algorithms and models of machine learning

Through practical situations, we make models for classification and prediction.

Example, whether a part of the text is written in a positive or negative tone, whether the mail is spam or not

How we make decisions in systems with complex rules


  1. scikit-img
  2. Percentile, standard deviation
  3. Histogram, scatter plot
  4. Split trening/test set, Linear regression
  5. Polinomial regression
  6. Logistic regression
  7. Decision tree
  8. Linear SVM classificator
  9. Perceptron
  10. Naive Bayes classificator
  11. NLP, Wordvec
  12. Bayes sentiment detection

The goal of this chapter is to learn the standard Python libraries and functions used in machine learning algorithms.


We use the following Python ML libraries: pandas, sclearn, SciPy, NumPy, scikit-image

5
Uber Ludwig

Deep learning tools, image classification, for example, a model that recognizes whether a picture is a dog or a cat. Sound classifications, prediction of the next number in the sequence, text classification.


  1. What is Ludvig, installation
  2. Text classification
  3. Sentiment analysis
  4. Image classification
  5. Titanik: survivor prediction
  6. Time series forecast
  7. Multilabel classification

The aim of this chapter is to learn the basics and principles of using Uber Ludwig tools to design, train and use deep learning models.

Sign up and learn it!
© All Rights Reserved. vladobra.com