Artificial Intelligence and Machine Learning: Complete Guide

Do you want to study AI and don't know where to start? You will learn everything you need to know in theory and practice

  • 0.0 (0 Reviews)
  • 0 Students
  • 189 Lessons
  • Jones Granatyr

Course Overview

The fields of Artificial Intelligence and Machine Learning are considered the most relevant areas in Information Technology. They are responsible for using intelligent algorithms to build software and hardware that simulate human capabilities. The job market for Machine Learning is on the rise in various parts of the world, and the trend is for professionals in this field to be in even higher demand. In fact, some studies suggest that knowledge in this area will soon become a prerequisite for IT professionals.

To guide you into this field, this course provides both theoretical and practical insights into the latest Artificial Intelligence techniques. This course is considered comprehensive because it covers everything from the basics to the most advanced techniques. By the end, you will have all the necessary tools to develop Artificial Intelligence solutions applicable to everyday business problems. The content is divided into seven parts: search algorithms, optimization algorithms, fuzzy logic, machine learning, neural networks and deep learning, natural language processing, and computer vision. You will learn the basic intuition of each of these topics and implement practical examples step by step. Below are some of the projects/topics that will be covered:


  • Finding optimal routes on city maps using greedy search and A* (star) search algorithms

  • Selection of the cheapest airline tickets and profit maximization using the following algorithms: hill climb, simulated annealing, and genetic algorithms

  • Prediction of the tip you would give to a restaurant using fuzzy logic

  • Classification using algorithms such as Naïve Bayes, decision trees, rules, k-NN, logistic regression, and neural networks

  • Prediction of house prices using linear regression

  • Clustering bank data using k-means algorithm

  • Generation of association rules with Apriori algorithm

  • Data preprocessing, dimensionality reduction, and outlier detection in databases

  • Prediction of stock prices using time series analysis

  • Data visualization and exploration in the context of the COVID-19 disease database

  • Building of a reinforcement learning agent to control a taxi for passenger transportation

  • Classification of cat and dog images using convolutional neural networks

  • Classification of Homer and Bart images from The Simpsons cartoon using convolutional neural networks

  • POS tagging, lemmatization, stemming, word cloud, and named entity recognition using natural language processing techniques

  • Implementation of a sentiment classifier in the context of a Twitter dataset

  • Face detection and recognition in images

  • Object tracking in videos

  • Generation of images that do not exist in the real world using advanced Computer Vision techniques

Each type of problem requires different techniques for its solution, so by covering all AI areas, you'll know which techniques to use in various scenarios! Throughout the course, we will use the Python programming language and the graphical tool Orange. If you are not familiar with Python, you will have access to over 5 hours of video exercises covering the basics of this programming language. This course is suitable for your first exposure to Artificial Intelligence, as it covers all the necessary topics in theory and practice. If you are more advanced in this field, you can use this course as a reference to learn new areas and review concepts.

See more

FAQ

FAQ area empty

Course curriculum

16 chương 189 bài học 22 giờ 13 phút 7 bài học thử miễn phí
Chương 1 Introduction
Chương 2 Part 1 - Search algorithms
Chương 3 Part 2 - Optimization algorithms
  • Optimization algorithms - intuition 6:45
  • Case study - flight schedule 2:32
  • Representing the problem 13:50
  • Printing the solution 15:43
  • Fitness function 8:50
  • Hill climb - intuition 8:00
  • Hill climb - implementation 3:50
  • Simulated annealing - intuition 4:35
  • Simulated annealing - implementation 5:05
  • Genetic algorithm - intuition 7:38
  • Genetic algorithm - implementation 4:53
  • HOMEWORK 4:22
  • Homework solution 8:23
Chương 4 Part 3 - Fuzzy logic
  • Introduction 1:18
  • Applications of fuzzy logic 3:55
  • Fuzzy logic - intuition 11:22
  • Implementation 1 8:15
  • Implementation 2 15:19
  • Implementation 3 5:34
  • HOMEWORK
  • Homework solution 7:19
Chương 5 Part 4 - Machine learning
  • Introduction 2:52
  • Machine learning and Data Science 6:16
Chương 6 Classification
  • What is classification? 9:35
  • Naïve Bayes - intuition 9:39
  • Naïve Bayes in Orange 18:09
  • Decision trees - intuition 4:56
  • Decision trees in Orange 3:17
  • Rule based learning - intuition 4:34
  • Rule based learning in Orange 3:32
  • KNN (k nearest neighbors) - intuition 9:41
  • KNN (k nearest neighbors) in Orange 2:33
  • SVM (Support Vectors Machines) - intuition 2:57
  • SVM (Support Vectors Machines) in Orange 2:07
  • Logistic regression - intuition 4:10
  • Logistic regression in Orange 4:54
  • Crossvalidation 4:45
  • HOMEWORK
  • Homework solution 6:12
  • Image classification in Orange 10:20
Chương 7 Regression
  • What is regression? 2:36
  • Linear regression - intuition 5:51
  • Linear regression in Orange 8:20
  • HOMEWORK
  • Homework solution 9:16
Chương 8 Clustering
  • What is clustering? 3:03
  • K-means algorithm - intuition 5:10
  • K-means algorithm in Orange 6:27
  • HOMEWORK
  • Homework solution 11:50
  • Clustering images in Orange 7:25
Chương 9 Association rules
  • What are association rules? 2:57
  • Apriori algorithm 10:13
  • Apriori in Orange 7:38
  • HOMEWORK
  • Homework solution 5:29
Chương 10 Additional topics
  • Missing values and normalization 11:57
  • Discretization 5:41
  • Feature selection 7:59
  • Dimensionality reduction using PCA 7:22
  • PCA and clustering 3:42
  • Outliers detection 8:25
  • Time series 1 6:35
  • Time series 2 9:23
  • Basic charts 6:27
  • COVID dataset 1 9:52
  • COVID dataset 2 10:14
  • COVID dataset 3 4:24
Chương 11 Reinforcement learning
  • Introduction 3:34
  • Intuition 18:50
  • Implementation 1 - environment 12:20
  • Implementation 2 - training 1 11:58
  • Implementation 3 - training 2 12:50
  • Implementation 4 - evaluation 10:20
Chương 12 Part 5 - Artificial neural networks and deep learning
  • Introduction 2:06
  • Biological fundamentals 5:42
  • Single layer perceptron 19:23
  • Multilayer perceptron – sum and activation functions 14:20
  • Multilayer perceptron – error calculation 5:19
  • Gradient descent 9:49
  • Delta parameter 8:09
  • Updating weights with backpropagation 14:03
  • Bias, error, stochastic gradient descent, and more parameters 17:56
  • Neural networks in Orange 7:33
  • Case study: Homer and Bart classification 3:38
  • Deep learning with TensorFlow 1 10:45
  • Deep learning with TensorFlow 2 8:45
  • Deep learning with TensorFlow 3 9:35
  • HOMEWORK
  • Homework solution 6:07
  • Introduction to convolutional neural networks 7:18
  • Convolutional operator 10:04
  • Pooling 5:28
  • Flattening 6:31
  • Dense neural network 5:10
  • Convolutional neural networks with TensorFlow 1 13:07
  • Convolutional neural networks with TensorFlow 2 16:10
  • HOMEWORK
  • Homework solution 6:32
  • Other types of neural networks
Chương 13 Part 6 - Natural language processing
  • Introduction 4:09
  • POS (part of speech), lemmatization, and stemming 16:42
  • Loading texts from the Internet 5:36
  • Text search using spaCy 11:34
  • Named entity recognition 3:06
  • Word cloud in Python 7:36
  • Word cloud in Orange 3:34
  • Sentiment analysis 1 7:22
  • Sentiment analysis 2 5:20
  • Sentiment analysis 3 12:20
  • Sentiment analysis 4 6:22
  • Sentiment analysis 5 6:40
  • Sentiment analysis 6 8:14
  • Sentiment analysis 7 5:15
  • Sentiment analysis 8 5:32
  • HOMEWORK
  • Text classification in Orange 6:31
Chương 14 Part 7 - Computer vision
  • Introduction 3:53
  • Images and pixels 4:40
  • Face detection - intuition 9:45
  • Face detection - implementation 17:49
  • HOMEWORK
  • Homework solution 5:24
  • Face recognition - intuition 9:25
  • Face recognition - training 12:56
  • Face recognition - classification 5:01
  • Object tracking - intuition 7:32
  • Object tracking - implementation 15:45
  • Image generation with Stable Diffusion 9:58
Chương 15 Additional content - Basic Python programming
  • Introduction to Python 4:09
  • Installation 7:34
  • Python IDEs 12:42
  • Variables and constants 14:08
  • Mathematical operations 5:59
  • Strings 11:06
  • HOMEWORK
  • Homework solution 4:43
  • Logical and relational operators 8:27
  • Conditional operators 10:25
  • HOMEWORK
  • Homework solution 7:41
  • Loops - for 11:16
  • Loops - while 10:25
  • HOMEWORK
  • Homework solution 5:45
  • Collections - tuples and lists 8:51
  • Collections - dictionaries and sets 9:56
  • Collections - matrices 7:02
  • HOMEWORK
  • Homework solution 8:01
  • Functions 10:07
  • HOMEWORK
  • Homework solution 5:53
  • Modules - math and datetime 9:43
  • Modules - random and time 11:10
  • Creating custom models 7:04
  • HOMEWORK
  • Homework solution 4:33
  • Errors and exceptions 14:22
  • HOMEWORK
  • Homework solution 3:58
  • Reading and writing text files 5:52
  • HOMEWORK
  • Homework solution 3:00
  • Regular expressions - intuition 13:06
  • Regular expressions - implementation 12:42
  • HOMEWORK
  • Homework solution 4:21
  • Object oriented - intuition 6:40
  • Object oriented - implementation 13:47
  • HOMEWORK
  • Homework solution 3:04
Chương 16 Final remarks
  • Final remarks 1:38
  • BONUS 1:32

Requirment

  • Programming logic

  • It is not necessary to know Python programming language, as at the end of the course there is an annex with basic classes if this is your first contact with it

Outcomes

  • The theoretical and practical basis of the main Artificial Intelligence algorithms

  • Implement Artificial Intelligence algorithms from scratch and using pre-defined libraries

  • Learn the intuition and practice about machine learning algorithms for classification, regression, association rules, and clustering

  • Learn Machine Learning without knowing a single line of code

  • Use Orange visual tool to create, analyze and test algorithms

  • Use Python programming language to create Artificial Intelligence algorithms

  • Learn the basics of programming in Python

  • Use greedy search and A* (A Star) algorithms to find the shortest path between cities

  • Implement optimization algorithms for minimization and maximization problems

  • Implement an AI to predict the amount of tip to be given in a restaurant, using fuzzy logic

  • Use data exploration techniques applied to a COVID-19 disease database

  • Create a reinforcement learning agent to simulate a taxi that needs to learn how to pick up and drop off passengers

  • Implement artificial neural networks and convolutional neural networks to classify images of the characters Homer and Bart, from the Simpsons cartoon

  • Learn natural language processing techniques and create a sentiment classifier

  • Detect and recognize faces using computer vision techniques

  • Track objects in video using computer vision

  • Generate new images that do not exist in the real world using Artificial Intelligence

Instructor

...
Jones Granatyr

0.0

  • ... 0 Student
  • ... 1 Course
  • ... 0 review

View Details

Reviews

Rate this course :

Remove all