The course is an invitation to the use of neural networks for binary classification problems, our main example of algorithm is the perceptron algorithm, the course is divided into classes of the

Following way:

1. What is Machine Learning?

2. A look at Python

3. Formal description of the Perceptron algorithm

4. Implementation of the perceptron algorithm for image classification

5. Neural networks in general.

​

​

Syllabus

​

​

1. Introduction

   • What is Machine Learning?

   • Mathematical notation

2. Python installation and a working environment for MachineLearning

   • Mini-microwave installation

   • Installation for Windows.

   • Installation for MacOS

   • Installation for Linux

   • Creation of a virtual environment for data analysis

   • Disable the base environment

   • Creation of a specific environment for data analysis using conda-forge

3. Perceptron

   • Theoretical justification of the algorithm of the perceptron

4. Binary classifier of microscopic images

5. Neural Networks

   • Expressive ability

   • Almost linearly separable data

   • Gradient method

   • Margin, over-adjustment and regularization

   • Convolutional neural networks and other activation functions

​