Bio-inspired Artificial Intelligence Algorithms

Focused View

Jones Granatyr,Guilherme Matos Passarini, phD,AI Expert Academy

8:23:10

11 View

1. Introduction

1. Couse content.mp4

04:32

2. Course materials.html

2. Genetic Algorithms

1.1 Source Code - Google Colab.html

1. Case study - flight schedule.mp4

04:54

2. Creating the variables.mp4

05:10

3. Flights dataset.mp4

12:30

4. Printing the schedule.mp4

16:53

5. Hours to minutes.mp4

05:14

6. Fitness function 1.mp4

11:55

7. Fitness function 2.mp4

08:08

8. Genetic algorithm - intuition.mp4

11:13

9. Part 1 - mutation.mp4

13:26

10. Part 2 - crossover.mp4

06:38

11. Part 3 - complete genetic algorithm.mp4

08:25

12. Part 4 - complete genetic algorithm.mp4

09:24

13. Part 5 - complete genetic algorithm.mp4

14:34

3. Differential Evolution

1.1 Project code.html

1. Introduction to the algorithm.mp4

04:04

2. General structure of the algorithm.mp4

05:03

3. The variation operator and the generation of new vectors.mp4

06:53

4. Main differences between DE and GA.mp4

03:14

5. Application nutrient allocation problem.mp4

03:45

6. Part 1 - Candidate solution.mp4

02:52

7. Part 2 - Population of vectors.mp4

02:16

8. Part 3 - Objetivefitness function.mp4

07:52

9. Part 4 - selecting three other vectors.mp4

04:05

10. Part 5 - variation operator.mp4

04:17

11. Part 6 - selecting the best vector from each population.mp4

02:03

12. Part 7 - running the algorithm.mp4

03:26

13. Part 8 - solution graph.mp4

03:11

4. Artificial Neural Networks

1.1 Source code - Google Colab.html

1. Biological fundamentals.mp4

05:42

2. Single layer perceptron.mp4

19:23

3. Multi-layer networks sum and activation functions.mp4

14:20

4. Multi-layer networks error calculation.mp4

05:19

5. Gradient descent.mp4

09:49

6. Delta parameter.mp4

08:09

7. Adjusting the weights with backpropagation.mp4

14:03

8. Bias, error, stochastic gradient descent, and more concepts.mp4

17:56

9. Part 1 - digits dataset.mp4

12:04

10. Part 2 - pre-processing the images.mp4

10:56

11. Part 3 - training.mp4

12:22

12. Part 4 - evaluating.mp4

10:19

13. Part 5 - classifying one single image.mp4

09:50

5. Clonal Selection Algorithm

1.1 Project code.html

1. Clonal Selection Algorithm.mp4

05:31

2. General structure of the algorithm.mp4

03:04

3. Calculating the cloning factor.mp4

04:51

4. Calculation of hypermutation.mp4

03:50

5. Application - Digit generationrecognition.mp4

03:47

6. Part 1 - antibody function.mp4

02:11

7. Part 2 - antibody population.mp4

01:41

8. Part 3 - fitness function.mp4

02:29

9. Part 4 - antibody affinity list.mp4

02:34

10. Part 5 - selecting the N best antibodies.mp4

03:06

11. Part 6 - cloning the best antibodies.mp4

04:26

12. Part 7 - Hypermutation of the antibodies.mp4

04:17

13. Part 8 - Running the algorithm.mp4

04:35

14. Part 9 - Solution graph.mp4

01:40

6. Particle Swarm Optimization

1.1 Project code.html

1. Introduction to the algorithm.mp4

05:36

2. General structure of the algorithm.mp4

03:44

3. Particles and the population (swarm).mp4

02:22

4. Individual best particle and Global best particle.mp4

02:08

5. Updating the position and velocity of the particles.mp4

04:01

6. Graphicalvectorial representation of positionvelocity update.mp4

03:19

7. Case study.mp4

06:47

8. Part 1 - Particle.mp4

05:00

9. Part 2 - Population.mp4

01:22

10. Part 3 - Fitness function.mp4

04:42

11. Part 4 - Personal best position (pbest).mp4

02:53

12. Part 5 - Global best position (gbest).mp4

04:00

13. Part 6 - Updating the position and velocity of the particle.mp4

03:44

14. Part 7 - New positionparticle.mp4

02:43

15. Part 8 - Running the algorithm.mp4

02:52

16. Part 9 - Solution graph.mp4

01:33

7. Ant Colony Optimization

1.1 Project code - part 1.html

1.2 Project code - part 2.html

1. Foraging behavior of ants.mp4

01:57

2. Foraging behavior of ants part 2.mp4

06:12

3. Update of pheromone deposition.mp4

06:18

4. Probability of edge selection.mp4

04:07

5. Ants and the TSP problem.mp4

06:05

6. Case study.mp4

03:31

7. Part 1 - Edges.mp4

03:42

8. Part 2 - Edge selection probability.mp4

04:21

9. Part 3 - Function that chooses edges.mp4

04:46

10. Part 4 - Generating pathsants.mp4

03:21

11. Part 5 - Path length function.mp4

01:37

12. Part 6 - Pheromone update.mp4

03:51

13. Part 7 - Running the algorithm.mp4

02:20

14. Part 8 - 5 nodes.mp4

02:32

15. Part 9 - Running the algorithm with 5 nodes.mp4

05:28

8. Final remarks

1. Final remarks.mp4

02:05

Description

Genetic algorithm, differential evolution, neural networks, clonal selection, particle swarm, ant colony optimization

What You'll Learn?

Understand the theory and practice of the main bio-inspired artificial intelligence algorithms
Solve real-world optimization problems using bio-inspired algorithms
Minimize the price of airline tickets using Genetic Algorithms
Create custom menus using Differential Evolution
Classify handwritten digits using Artificial Neural Networks
Adapt antibodies and antigens with the Clonal Selection algorithm, applied in digit recognition
Optimize course schedules using Particle Swarm Optimization
Solve shortest paths problems using Ant Colony Optimization

Who is this for?

People interested in how nature can provide inspiration for Computer Science problems

People interested in artificial intelligence algorithms, especially those inspired in Biology

Developers who want to solve real optimization and classification problems

Data Scientists who want to increase their portfolio

What You Need to Know?

Programming logic

Basic Python programming

More details

Description
Nature offers a wide range of inspirations for biological processes to be incorporated into technology and computing. Some of these processes and patterns have been inspiring the development of algorithms that can be used to solve real-world problems. They are called bio-inspired algorithms, whose inspiration in nature allows for applications in various optimization and classification problems.
In this course, you will learn the theoretical and mainly the practical implementation of the main and mostly used bio-inspired algorithms! By the end of the course you will have all the tools you need to build artificial intelligence solutions that can be applied to your own problems! The course is divided into six sections that cover different algorithms applied in real-world case studies. See below the projects that will be implemented step by step:

Genetic Algorithms (GA): It is one of the most used and well-known bio-inspired algorithm to solve optimization problems. It is based on biological evolution in which populations of individuals evolve over generations through mutation, selection, and crossing over. We will solve the flight schedule problem and the goal is to minimize the price of air line tickets and the time spend waiting at the airport.
Differential Evolution (DE): It is also inspired in biological evolution and the case study we will solve step by step is the creation of menus, correctly balancing the amount of carbohydrates, proteins and fats.
Neural Networks (ANN): It is based on how biological neurons work and is considered one of the most modern techniques to solve complex problems, such as: chatbots, automatic translators, self driving cars, voice recognition, among many others. The case study will be the creation of a neural network for image classification.
Clonal Selection Algorithm (CSA): It is based on the functioning of the optimization of the antibody response against an antigen, resembling the process of biological evolution. These concepts will be used in practice for digit identification and digit generation.
Particle Swarm Optimization (PSO): It relies on the social behavior of animals, in which the swarm tries to find the best solution to a specific problem. The problem to be solved will be the timetable: there is a course, people who want to take it and different timetables. In the end, the algorithm will indicate the best times for each class to take the course.
Ant Colony Optimization (ACO): It is based on concepts of how ants search for food in nature. The case study will be one of the most classic in the area, which is the choice of the shortest path.
Each type of problem requires different techniques for its solution. When you understand the intuition and implementation of bio-inspired algorithms, it is easier to identify which techniques are the best to be applied in each scenario. During the course, all the code will be implemented step by step using the Python programming language! We are going to use Google Colab, so you do not have to worry about installing libraries on your machine, as everything will be developed online using Google's GPUs!
Who this course is for:
People interested in how nature can provide inspiration for Computer Science problems
People interested in artificial intelligence algorithms, especially those inspired in Biology
Developers who want to solve real optimization and classification problems
Data Scientists who want to increase their portfolio

User Reviews

Rating

average 0

Total votes0

Focused display

Olá! Meu nome é Jones Granatyr e já trabalho em torno de 10 anos com Inteligência Artificial (IA), inclusive fiz o meu mestrado e doutorado nessa área. Atualmente sou professor, pesquisador e fundador do portal IA Expert, um site com conteúdo específico sobre Inteligência Artificial. Desde que iniciei na Udemy criei vários cursos sobre diversos assuntos de IA, como por exemplo: Deep Learning, Machine Learning, Data Science, Redes Neurais Artificiais, Algoritmos Genéticos, Detecção e Reconhecimento Facial, Algoritmos de Busca, Mineração de Textos, Buscas em Textos, Mineração de Regras de Associação, Sistemas Especialistas e Sistemas de Recomendação. Os cursos são abordados em diversas linguagens de programação (Python, R e Java) e com várias ferramentas/tecnologias (tensorflow, keras, pandas, sklearn, opencv, dlib, weka, nltk, por exemplo). Meu principal objetivo é desmistificar a área de IA e ajudar profissionais de TI a entenderem como essa tecnologia pode ser utilizada na prática e que possam visualizar novas oportunidades de negócios.

Guilherme Matos Passarini, phD

Instructor's Courses

English:Hi, my name is Guilherme, I have a bachelor's degree in Biological Sciences, a master's degree in Experimental Biology, and a Ph.D. also in Experimental Biology, both from the Federal University of Rondônia (Brazil). My main research area is the search for compounds that are active against the parasites of malaria and leishmaniasis. I also have been programming for a while, especially in the programming languages Python and R. My main interests are biology, biotechnology, programming, medicinal chemistry, and artificial intelligence. My main goal here in Udemy is therefore spreading the knowledge related to these areas to people around the world.Português:Bacharel e licenciado em Ciências Biológicas pela Universidade Federal de Rondônia, mestre em Biologia Experimental pela Universidade Federal de Rondônia e doutor também em Biologia Experimental pela Universidade Federal de Rondônia. Desenvolveu seus trabalhos de iniciação científica e mestrado na busca de moléculas de plantas bioativas contra os parasitas da malária e leishmaniose, tendo trabalhado com fitoquímica e ensaios antiparasitários in vitro. No final do mestrado, começou a se interessar por bioinformática, química medicinal e programação, aplicando alguns programas de bioinformática e quimioinformática para auxiliar na descoberta de drogas antimaláricas. Possui experiência com as linguagens Python e R, e iniciou a programar em Javascript. Seu projeto de doutorado se constitui em avaliar um composto antimalárico já testado durante o mestrado de forma mais aprofundada contra o parasita da malária, realizando análises virtuais, como verificação de características físico-químicas e farmacocinéticas, docking molecular (interação virtual entre ligante e proteína-alvo do parasita) e ensaios em placas de cultura.

AI Expert Academy

Instructor's Courses

We are an on-line platform focused on courses on Artificial Intelligence, Machine Learning and Data Science. Our goal is to offer easy-to-understand theoretical and practical content, so that professionals from all areas can understand the benefits that AI can bring to their businesses. We are established in Brazil since 2018 and we have already published more than 90 courses in English and Portuguese on the Udemy platform.

Udemy

View courses Udemy

Students take courses primarily to improve job-related skills.Some courses generate credit toward technical certification. Udemy has made a special effort to attract corporate trainers seeking to create coursework for employees of their company.