Text Mining Course

This course will explore Text Mining, a fascinating field that extracts knowledge from unstructured data such as text, social media, and online reviews. We will learn how to transform this raw data into useful information for various applications, such as sentiment analysis, text classification, and information extraction.

What topics will we cover?

1. Definition of Unstructured Data
2. Overview of Text Mining areas
3. Pipeline of a typical Text Mining project:

1. • Text pre-processing
   • Text vectorization:
   • Data preparation
   • Modelling
   • Evaluation
   • Deployment

1. Representation techniques:
   • Word2Vec
   • Glove
2. Practical applications

What material will be provided in the course?

1. Slides
2. Use cases in Python

Advanced Machine Learning Course

This course is a deep dive into the world of Deep Learning, exploring its techniques and real-world applications. Aimed at those already familiar with the basics of Machine Learning, the course delves into neural networks, Deep Learning models, and their practical use in Python.

What topics will we cover?

1.  Neural Networks and Deep Learning
   • Introduction to Deep Learning models
   • Artificial Intelligence vs Machine Learning vs Deep Learning
   • Neural Network Topology
2. Keras
   • Python framework
   • Back-end engine
   • Alternative Python libraries
3. Perceptron
   • Mathematical definition
   • Training process
   • Hyperparameters
   • Regularization methods
4. Feed Forward Neural Networks
5. Multi-Layer Neural Networks
   • Data preparation techniques
   • Activation functions
   • Loss functions
   • Backpropagation algorithm
6. Autoencoders
7. Neural Networks for Unsupervised Learning
   • Architecture
   • Hyperparameters
8.  Convolutional Neural Networks
   • Computer vision
   • MLNN vs CNN
   • Architecture
   • Training
   • Data types for CNNs
   • Examples of well-known model
9.  Recurrent Neural Networks
   • Text mining
   • Architecture
   • RNN Cell
   • Training (Backpropagation Through Time algorithm)
   • Long-Short Term Memory Networks

What material will be provided in the course?

1. Slides
2. Python use cases

Computer Vision Course

In today’s digital age, data is the key to success. Companies that can extract value from unstructured data, such as images and videos, gain an invaluable competitive advantage. Computer Vision, powered by Deep Learning, offers the ideal solution for transforming this data into actionable insights, opening up new frontiers for innovation and growth.

What topics will we cover?

1. Definition of Unstructured Data
2. Definition of Computer Vision and examples of practical applications
3. Overview of the fields of application of Computer Vision
4. The role of Machine Learning and Deep Learning in Computer Vision
5. How do PCs read images?
6. Convolutional Neural Networks:
   • 1D, 2D, 3D
7. Data Manipulation:
   • Data Pre-Processing
   • Data Augmentation
8. Use cases and examples:
   • Classification
   • Object Localization
   • Landmark Detection
   • Object Detection (sliding window algorithm):
   • YOLO

What materials will be provided in the course?

1. Slides
2. Use cases in Python

ML Base Course

In this introductory course, you will discover the key concepts of Machine Learning and its real-world applications. You will learn to build machine learning models using Python, one of the most popular libraries for Machine Learning.

What topics will we cover?

1. Introduction to Machine Learning:
   • Definitions and key concepts of Machine Learning
   • Examples of applications
   • AI vs Mach Learning vs Deep Learning
2. Building a Dataset
3. Supervised and Unsupervised Learning Problems
4. Basic Mathematics of a Machine Learning Project:
   • Loss function
   • Gradient descent
   • Error on the test set
   • Performance metrics
   • Bias-Variance trade-off
5. Common Problems to Solve:
   • Overfitting
   • Regularization of the cost function
6. Hyperparameter Tuning:
   • Cross Validation
7. Pipeline of a typical Machine Learning project:
   • Data preprocessing
8. Famous Machine Learning Models:
   • Decision Trees
   • Perceptron
   • Introduction to Neural Networks

What materials will be provided in the course?

1. Explanatory slides
2. Practical examples in Python to consolidate your knowledge