We may earn an affiliate commission when you visit our partners.

Art and Science of Machine Learning em Português Brasileiro

Este é o curso Art and Science of Machine Learning. O curso tem seis módulos. Falaremos sobre as habilidades essenciais de intuição, bom senso e experimentação em ML para ajustar e otimizar modelos e ter melhor desempenho. Você aprenderá a generalizar os modelos usando técnicas de regularização e conhecerá os efeitos dos hiperparâmetros, como tamanho de lote e taxa de aprendizado, sobre o desempenho do modelo. Também abordaremos alguns algoritmos mais comuns de otimização de modelo e mostraremos como especificar um método de otimização no código do TensorFlow.

Enroll now

Or subscribe to Coursera Plus

And get unlimited access to Coursera

Here's a deal for you

Save money when you learn with a deal that may be relevant to this course.

All coupon codes, vouchers, and discounts are applied automatically unless otherwise noted.

Valid until August 30

Google AI App Builder

Learn how to use Gemini API and API Studio with a three-course series from Google DeepMind

What's inside

Syllabus

Introdução

Este é o curso Art and Science of Machine Learning. Falaremos sobre as habilidades essenciais de intuição, bom senso e experimentação em ML para ajustar e otimizar modelos e ter melhor desempenho. Você aprenderá a generalizar os modelos usando técnicas de regularização e conhecerá os efeitos dos hiperparâmetros, como tamanho de lote e taxa de aprendizado, sobre o desempenho do modelo. Também abordaremos alguns algoritmos mais comuns de otimização de modelo e mostraremos como especificar um método de otimização no código do TensorFlow.

Traffic lights

Read about what's good

what should give you pause

and possible dealbreakers

Pode ajudar alunos iniciantes a aprimorar suas habilidades básicas de ML

Desenvolve habilidades essenciais em ML, como intuição, bom senso e experimentação

Ajuda alunos a otimizar e ajustar modelos de ML para melhorar o desempenho

Oferece uma introdução à teoria e técnicas comuns de otimização de modelos

Requer que os alunos tenham algum conhecimento prévio de ML

Save this course

Create your own learning path. Save this course to your list so you can find it easily later.

Save

Reviews summary

Ml prático e intuitivo em português

De acordo com os alunos, este curso oferece uma base sólida e prática em Machine Learning, destacando a intuição e experimentação essenciais para o ajuste e otimização de modelos. Muitos elogiam a abordagem que combina a 'arte' do ML com sua 'ciência', cobrindo tópicos como regularização, hiperparâmetros e redes neurais. A implementação em TensorFlow é vista como um ponto forte, fornecendo habilidades aplicáveis. Alguns mencionam que, para maior profundidade em certas áreas, o estudo adicional pode ser necessário, mas a clareza dos instrutores e a disponibilidade em Português Brasileiro são consistentemente valorizadas.

Foco em exemplos e implementação de conceitos em código.

"Aprender a especificar métodos de otimização no código do TensorFlow foi muito útil e direto ao ponto."

"Os exemplos práticos com TensorFlow solidificaram meu entendimento de hiperparâmetros e regularização."

"Saí do curso sabendo como aplicar o que aprendi diretamente em projetos com TensorFlow, o que é um grande diferencial."

Combina a arte da intuição com a ciência da otimização de modelos.

"O curso realmente me ensinou a pensar como um cientista de ML, balanceando intuição e dados para ajustar modelos."

"Adorei a parte da 'arte do ML', que me ajudou a entender a lógica por trás da experimentação e do bom senso."

"Não é só teoria; a abordagem me deu ferramentas práticas e a mentalidade para otimizar meus próprios modelos."

Disponibilidade na língua nativa facilita o aprendizado.

"Ter um curso de ML de alta qualidade em português brasileiro foi um alívio e facilitou muito a compreensão de conceitos complexos."

"A tradução é excelente e o sotaque dos instrutores é natural, tornando a experiência de aprendizado muito agradável."

"Finalmente um curso avançado de ML que eu posso acompanhar sem a barreira do idioma. Recomendo para todos os falantes de português."

Bom para iniciantes, mas pode exigir estudo adicional.

"Para quem já tem alguma base em ML, algumas partes podem parecer introdutórias demais, mas ainda assim é uma boa revisão."

"Senti que alguns tópicos poderiam ser mais aprofundados, exigindo que eu buscasse material extra para complementar."

"Se você é um iniciante, este curso é ótimo para começar, mas não espere se tornar um expert em todas as áreas apenas com ele."

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Art and Science of Machine Learning em Português Brasileiro with these activities:

Revise the fundamentals of machine learning

Show steps

Revising the fundamentals of machine learning will provide you with a strong foundation and make it easier to grasp the advanced concepts covered in the course.

Browse courses on Machine Learning Basics

Show steps

Review your notes or textbooks on machine learning concepts such as supervised and unsupervised learning, feature engineering, and model evaluation.
Solve practice problems or take online quizzes to test your understanding of the core principles.
Attend a workshop or webinar on machine learning to refresh your knowledge and learn about the latest advancements in the field.

Connect with experienced machine learning professionals

Show steps

Mentorship provides guidance, support, and valuable insights.

Show steps

Identify potential mentors in your network or through online platforms.
Reach out to mentors and express your interest in learning from them.
Schedule regular meetings to discuss your progress and seek advice.

Participate in peer study groups

Show steps

Participating in peer study groups will provide you with opportunities to discuss course material, ask questions, and learn from your peers.

Show steps

Find a study group or create your own with classmates.
Meet regularly to discuss the course material, work on assignments, and prepare for exams.
Take turns leading discussions and presenting your understanding of different concepts.

11 other activities

Expand to see all activities and additional details

Show all 14 activities

Revise linear algebra

Show steps

Linear algebra is essential for understanding the mathematical foundations of machine learning algorithms.

Browse courses on Matrix Operations

Show steps

Review the basics of matrix operations, such as addition, subtraction, and multiplication.
Understand the concept of vector spaces and subspaces.
Learn about linear transformations and their properties.

Practice tuning hyperparameters

Show steps

Practicing tuning hyperparameters will help you develop the skills necessary to optimize your machine learning models and improve their performance.

Browse courses on Hyperparameter Tuning

Show steps

Experiment with different hyperparameter settings for a given machine learning algorithm.
Use a hyperparameter optimization library to automate the process and find the best settings for your model.
Compare the performance of your model before and after hyperparameter tuning to see the impact of your changes.

Solve machine learning practice problems

Show steps

Solving practice problems helps reinforce the concepts learned in the course and improve problem-solving skills.

Browse courses on Supervised Learning

Show steps

Find practice problems online or in textbooks.
Start with easier problems and gradually move on to more challenging ones.
Check your solutions and identify areas for improvement.

Join a machine learning study group

Show steps

Participating in a study group provides opportunities for collaboration and knowledge sharing.

Show steps

Find a study group or create your own.
Meet regularly to discuss course material, work on projects, and share ideas.
Provide feedback and support to other group members.

Participate in machine learning competitions

Show steps

Participating in competitions helps you benchmark your skills and learn from others.

Show steps

Choose competitions that are relevant to your interests and skill level.
Form a team or work individually.
Develop and submit your solutions.
Analyze the results and identify areas for improvement.

Contribute to open-source machine learning projects

Show steps

Open-source contributions demonstrate your skills and help you connect with the machine learning community.

Show steps

Find open-source projects that align with your interests.
Start by contributing small fixes or improvements.
Gradually take on larger responsibilities and become a regular contributor.

Follow tutorials on advanced machine learning techniques

Show steps

Following tutorials provides hands-on experience with cutting-edge machine learning techniques.

Browse courses on Natural Language Processing

Show steps

Identify areas where you want to deepen your knowledge.
Find reputable online tutorials or courses that cover those topics.
Follow the tutorials step-by-step and implement the techniques in your own projects.

Follow tutorials on advanced machine learning techniques

Show steps

Following tutorials on advanced machine learning techniques will expose you to new concepts and algorithms and help you expand your knowledge in the field.

Browse courses on Deep Learning

Show steps

Identify specific advanced machine learning techniques that you are interested in learning.
Search for online tutorials or courses that cover these techniques.
Follow the tutorials step-by-step and implement the techniques in your own projects.

Build a machine learning portfolio

Show steps

Building a portfolio showcases your skills and knowledge, and helps you stand out in the job market.

Show steps

Choose projects that align with your interests and career goals.
Gather data and explore different machine learning algorithms.
Build and train models, and evaluate their performance.
Deploy your models and track their impact.

Contribute to open-source machine learning projects

Show steps

Contributing to open-source machine learning projects will give you hands-on experience, allow you to learn from others, and help advance the field.

Browse courses on Community Involvement

Show steps

Identify open-source machine learning projects that align with your interests.
Start by contributing small changes or bug fixes.
Gradually take on larger tasks and responsibilities as you become more familiar with the project.

Build a machine learning project

Show steps

Building a machine learning project will allow you to apply the concepts learned in the course to a real-world problem and demonstrate your skills and understanding.

Show steps

Define the problem you want to solve and gather the necessary data.
Choose appropriate machine learning algorithms and train your models.
Evaluate the performance of your models and make improvements as needed.
Deploy your model and monitor its performance in a real-world setting.

Career center

Learners who complete Art and Science of Machine Learning em Português Brasileiro will develop knowledge and skills that may be useful to these careers:

Machine Learning Researcher

Machine Learning Researchers develop new machine learning algorithms and techniques. They work with a variety of data sources and technologies to push the boundaries of machine learning. This course may be useful for Machine Learning Researchers who want to improve their understanding of the art and science of machine learning. The course covers topics such as adjusting the size of batches and learning rates, optimizing models, and applying these concepts to TensorFlow code.

See salaries and explore the career path for Machine Learning Researcher

Artificial Intelligence Engineer

Artificial Intelligence Engineers design, develop, and maintain artificial intelligence systems. They work with a variety of programming languages and technologies to create systems that can learn from data and make decisions. This course may be useful for Artificial Intelligence Engineers who want to improve their understanding of the art and science of machine learning. The course covers topics such as adjusting the size of batches and learning rates, optimizing models, and applying these concepts to TensorFlow code.

See salaries and explore the career path for Artificial Intelligence Engineer

Quantitative Analyst

Quantitative Analysts use mathematical and statistical models to analyze financial data and make investment decisions. They develop and apply machine learning models to identify trading opportunities and manage risk. This course may be useful for Quantitative Analysts who want to improve their understanding of the art and science of machine learning. The course covers topics such as adjusting the size of batches and learning rates, optimizing models, and applying these concepts to TensorFlow code.

See salaries and explore the career path for Quantitative Analyst

Computer Vision Engineer

Computer Vision Engineers design, develop, and maintain computer vision systems. They work with a variety of image and video data to create systems that can recognize objects, track motion, and understand the content of images and videos. This course may be useful for Computer Vision Engineers who want to improve their understanding of the art and science of machine learning. The course covers topics such as adjusting the size of batches and learning rates, optimizing models, and applying these concepts to TensorFlow code.

See salaries and explore the career path for Computer Vision Engineer

Natural Language Processing Engineer

Natural Language Processing Engineers design, develop, and maintain natural language processing systems. They work with a variety of text and speech data to create systems that can understand human language. This course may be useful for Natural Language Processing Engineers who want to improve their understanding of the art and science of machine learning. The course covers topics such as adjusting the size of batches and learning rates, optimizing models, and applying these concepts to TensorFlow code.

See salaries and explore the career path for Natural Language Processing Engineer

Machine Learning Engineer

Machine Learning Engineers implement, maintain, and improve machine learning systems. They work closely with data scientists to bring machine learning models into production. This course may be useful for Machine Learning Engineers who want to improve their understanding of the art and science of machine learning. The course covers topics such as adjusting the size of batches and learning rates, optimizing models, and applying these concepts to TensorFlow code.

See salaries and explore the career path for Machine Learning Engineer

Data Scientist

Data Scientists use their knowledge of mathematics, statistics, and computer science to extract meaningful insights from data. They develop and apply machine learning models to solve business problems. This course may be useful for Data Scientists who want to improve their understanding of the art and science of machine learning. The course covers topics such as adjusting the size of batches and learning rates, optimizing models, and applying these concepts to TensorFlow code.

See salaries and explore the career path for Data Scientist

Business Analyst

Business Analysts use data and analysis to help businesses make better decisions. They work with a variety of stakeholders to identify business problems and develop solutions. This course may be useful for Business Analysts who want to learn more about machine learning and how to apply it to their work. The course covers topics such as adjusting the size of batches and learning rates, optimizing models, and applying these concepts to TensorFlow code.

See salaries and explore the career path for Business Analyst

Software Engineer

Software Engineers design, develop, and maintain software systems. They work with a variety of programming languages and technologies to create software that meets the needs of users. This course may be useful for Software Engineers who want to learn more about machine learning and how to apply it to their work. The course covers topics such as adjusting the size of batches and learning rates, optimizing models, and applying these concepts to TensorFlow code.

See salaries and explore the career path for Software Engineer

Business Intelligence Analyst

Business Intelligence Analysts use data to help businesses make better decisions. They work with a variety of data sources and technologies to analyze data and identify trends. This course may be useful for Business Intelligence Analysts who want to learn more about machine learning and how to apply it to their work. The course covers topics such as adjusting the size of batches and learning rates, optimizing models, and applying these concepts to TensorFlow code.

See salaries and explore the career path for Business Intelligence Analyst

Data Analyst

Data Analysts use data to solve business problems. They work with a variety of data sources and technologies to analyze data and identify trends. This course may be useful for Data Analysts who want to learn more about machine learning and how to apply it to their work. The course covers topics such as adjusting the size of batches and learning rates, optimizing models, and applying these concepts to TensorFlow code.

See salaries and explore the career path for Data Analyst

Data Engineer

Data Engineers design, build, and maintain data pipelines. They work with a variety of data sources and technologies to ensure that data is clean, consistent, and accessible. This course may be useful for Data Engineers who want to learn more about machine learning and how to apply it to their work. The course covers topics such as adjusting the size of batches and learning rates, optimizing models, and applying these concepts to TensorFlow code.

See salaries and explore the career path for Data Engineer

Robotics Engineer

Robotics Engineers design, develop, and maintain robots. They work with a variety of hardware and software to create robots that can perform a variety of tasks, such as walking, talking, and interacting with the environment. This course may be useful for Robotics Engineers who want to learn more about machine learning and how to apply it to their work. The course covers topics such as adjusting the size of batches and learning rates, optimizing models, and applying these concepts to TensorFlow code.

See salaries and explore the career path for Robotics Engineer

Product Manager

Product Managers are responsible for the development and launch of new products. They work with a variety of stakeholders to define product requirements, prioritize features, and track progress. This course may be useful for Product Managers who want to learn more about machine learning and how to apply it to their work. The course covers topics such as adjusting the size of batches and learning rates, optimizing models, and applying these concepts to TensorFlow code.

See salaries and explore the career path for Product Manager

Project Manager

Project Managers are responsible for planning, executing, and closing projects. They work with a variety of stakeholders to define project goals, develop project plans, and track progress. This course may be useful for Project Managers who want to learn more about machine learning and how to apply it to their work. The course covers topics such as adjusting the size of batches and learning rates, optimizing models, and applying these concepts to TensorFlow code.

See salaries and explore the career path for Project Manager

Reading list

We've selected 11 books that we think will supplement your learning. Use these to develop background knowledge, enrich your coursework, and gain a deeper understanding of the topics covered in Art and Science of Machine Learning em Português Brasileiro.

Deep Learning

Save

Este livro abrangente é uma referência essencial para aprendizado profundo. Ele cobre os fundamentos teóricos e práticos do aprendizado profundo, incluindo redes neurais, convolução e processamento de linguagem natural.

(English) Deep Learning

Paperback

$$$

(English) Deep Learning (Adaptive Computation and Machine...

Hardcover

$$$

(English) Deep Learning (Adaptive Computation and Machine...