AI Workflow: Machine Learning, Visual Recognition and NLP from Coursera

This is the fourth course in the IBM AI Enterprise Workflow Certification specialization. You are STRONGLY encouraged to complete these courses in order as they are not individual independent courses, but part of a workflow where each course builds on the previous ones.

Course 4 covers the next stage of the workflow, setting up models and their associated data pipelines for a hypothetical streaming media company. The first topic covers the complex topic of evaluation metrics, where you will learn best practices for a number of different metrics including regression metrics, classification metrics, and multi-class metrics, which you will use to select the best model for your business challenge. The next topics cover best practices for different types of models including linear models, tree-based models, and neural networks. Out-of-the-box Watson models for natural language understanding and visual recognition will be used. There will be case studies focusing on natural language processing and on image analysis to provide realistic context for the model pipelines.

By the end of this course you will be able to:

Discuss common regression, classification, and multilabel classification metrics

Explain the use of linear and logistic regression in supervised learning applications

Describe common strategies for grid searching and cross-validation

Employ evaluation metrics to select models for production use

Explain the use of tree-based algorithms in supervised learning applications

Explain the use of Neural Networks in supervised learning applications

Discuss the major variants of neural networks and recent advances

Create a neural net model in Tensorflow

Create and test an instance of Watson Visual Recognition

Create and test an instance of Watson NLU

Who should take this course?

This course targets existing data science practitioners that have expertise building machine learning models, who want to deepen their skills on building and deploying AI in large enterprises. If you are an aspiring Data Scientist, this course is NOT for you as you need real world expertise to benefit from the content of these courses.

What skills should you have?

It is assumed that you have completed Courses 1 through 3 of the IBM AI Enterprise Workflow specialization and you have a solid understanding of the following topics prior to starting this course: Fundamental understanding of Linear Algebra; Understand sampling, probability theory, and probability distributions; Knowledge of descriptive and inferential statistical concepts; General understanding of machine learning techniques and best practices; Practiced understanding of Python and the packages commonly used in data science: NumPy, Pandas, matplotlib, scikit-learn; Familiarity with IBM Watson Studio; Familiarity with the design thinking process.

What's inside

Syllabus

Model Evaluation and Performance Metrics

This week covers model selection, evaluation and performance metrics. The focus is on evaluating models iteratively for improvements. You will survey the landscape of evaluation metrics and linear models in order to ensure you are comfortable using implementing baseline models. The materials build up to the case study where you will use natural language processing in a classification setting. When you are done iterating on your model you will connect its model performance to business metrics as an approach to better understand model utility.

Building Machine Learning and Deep Learning Models

This week is primarily focused on building supervised learning models. We will survey available methods in two popular and effective areas of machine learning: Tree based algorithms and deep learning algorithms. We will cover the use of tree based methods like random forests and boosting along with other ensemble approaches. Many of these approaches serve as an important middle layer between interpretable linear models and difficult to interpret deep-learning models. For deep learning we will use a pre-built visual recognition model and use TensorFlow to demonstrate how to build, tune, and iterate on neural networks. We will also make sure that you understand popular neural network architectures. In the case study you will implement a convolutional neural network and ready it for deployment.

Good to know

Know what's good

, what to watch for

, and possible dealbreakers

Taught by recognized experts in their field, Mark J Grover and Ray Lopez, Ph.D., who are highly regarded for their work in the data science industry

Assumes learners have specific background knowledge in machine learning, linear algebra, statistical concepts, and data science packages, making it suitable for experienced professionals looking to deepen their skills in AI implementation

Provides hands-on experience through case studies in natural language processing and image analysis, offering practical insights into real-world AI applications

Focuses on evaluation metrics and model selection, emphasizing the importance of selecting the best model for a given business challenge using industry best practices

Covers a range of models, including linear models, tree-based models, and neural networks, providing a comprehensive understanding of different modeling techniques

Designed for data science practitioners seeking to advance their skills in building and deploying AI solutions within large enterprises

Reviews summary

In-depth course for ml, visual recognition, nlp

According to students, AI Workflow: Machine Learning, Visual Recognition and NLP is an engaging course that covers machine learning, visual recognition, and NLP. Students say that the teaching materials are well presented and easy to follow with plenty of practice. A few students note that some of the terminology could be confusing, especially for beginners to machine learning, but overall, they say it is a valuable course.

Students enjoyed the course's content.

"very Informative"

"Great training !!!"

"The teaching materials are well presented and clear."

The course content is explained clearly.

"Its pretty difficult to follow up with this course."

"The video quality was, for the most part, very well done"

The course's terminology can be confusing at times.

"Aspects of this course could be worked on with regards to smoothness, conceptual teaching and grammatical/spelling errors."

"Much of the course had confusing terminology/grammatical forms which made multiple lessons difficult to understand."

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 AI Workflow: Machine Learning, Visual Recognition and NLP with these activities:

Create a simple regression model using scikit-learn

Show steps

This activity will help you refresh your understanding of linear regression and ensure you have the necessary skills to build and evaluate simple regression models using scikit-learn.

Browse courses on Linear Regression

Show steps

Review the basics of linear regression
Create a simple regression model using scikit-learn
Evaluate the performance of your model

Identify a mentor who can guide you in your machine learning journey

Show steps

This activity will connect you with an experienced professional who can provide valuable guidance, support, and insights as you navigate your machine learning career.

Browse courses on Mentorship

Show steps

Attend industry events and conferences
Reach out to potential mentors through LinkedIn or email
Build a mutually beneficial relationship with your mentor

Write a blog post summarizing a key concept from the course

Show steps

This activity will improve your ability to synthesize and communicate complex technical concepts, enhancing your understanding and solidifying your knowledge.

Browse courses on Communication Skills

Show steps

Choose a key concept from the course
Research and gather information on the topic
Write a blog post that clearly explains the concept
Publish your blog post and share it with others

Five other activities

Expand to see all activities and additional details

Show all eight activities

Practice evaluating regression metrics

Show steps

This activity will help you strengthen your understanding of regression metrics and gain proficiency in evaluating the performance of regression models.

Browse courses on Model Evaluation

Show steps

Solve practice problems on regression metrics
Analyze the results of your solutions

Read 'Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow' by Aurélien Géron

Show steps

This book provides a comprehensive overview of machine learning concepts and practical implementations using popular Python libraries, reinforcing your understanding and expanding your technical knowledge.

View Hands-On Machine Learning with Scikit-Learn,... on Amazon

Show steps

Read the book thoroughly and take notes
Work through the code examples and exercises
Apply what you learned to your own projects

Build a classification model for a real-world dataset

Show steps

This activity will provide you with hands-on experience in building and evaluating a classification model using a real-world dataset, which will enhance your practical skills in machine learning.

Browse courses on Classification Models

Show steps

Choose a real-world dataset
Preprocess and explore the data
Train and evaluate a classification model
Interpret and present your results

Attend a workshop on deep learning for natural language processing

Show steps

This activity will expose you to advanced deep learning techniques and their application in natural language processing, broadening your knowledge and skills in this specialized area.

Browse courses on Deep Learning

Show steps

Register for a workshop on deep learning for natural language processing
Attend the workshop and actively participate
Apply what you learned to a personal project

Participate in a machine learning competition

Show steps

This activity will challenge you to apply your skills in a competitive environment, fostering your problem-solving abilities, resilience, and ability to work under pressure.

Browse courses on Model Optimization

Show steps

Identify a machine learning competition that aligns with your interests
Study the competition guidelines and dataset
Build and train your machine learning models
Submit your results and analyze your performance

Career center

Learners who complete AI Workflow: Machine Learning, Visual Recognition and NLP will develop knowledge and skills that may be useful to these careers:

Machine Learning Engineer

The Machine Learning Engineer is responsible for designing, building, and deploying machine learning models. This course can help you build the skills you need to succeed in this role by providing you with a strong foundation in model evaluation and performance metrics, as well as experience building machine learning and deep learning models. You will also learn how to connect your model performance to business metrics, which is essential for understanding model utility.

See salaries and explore the career path for Machine Learning Engineer

Data Scientist

Responsible for collecting, analyzing, and interpreting data to help businesses make better decisions, Data Scientists use machine learning to build predictive models. This course can help you build the skills you need for this role by providing you with a strong understanding of the machine learning landscape as well as how to monitor models in production. The case study in this course, which demonstrates how to implement a convolutional neural network and ready it for deployment, can be especially helpful.

See salaries and explore the career path for Data Scientist

Natural Language Processing Engineer

Responsible for building and maintaining natural language processing models, the Natural Language Processing Engineer uses machine learning to help computers understand and generate human language. This course will help you build the skills you need for this role through in-depth lessons on building natural language processing models as well as industry best practices for iteratively improving and deploying them.

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

Software Engineer

Software Engineers design, develop, and maintain software applications. Machine learning is becoming increasingly important in this field, and this course can help you build the skills you need to succeed as a Software Engineer in this new era. You will learn how to build and deploy machine learning models, as well as how to connect your model performance to business metrics.

See salaries and explore the career path for Software Engineer

Quantitative Analyst

The Quantitative Analyst uses mathematical and statistical techniques to analyze data and build financial models. Machine learning is becoming increasingly important in this field, and this course can help you build the skills you need to succeed as a Quantitative Analyst in this new era. You will learn how to build and deploy machine learning models, as well as how to connect your model performance to business metrics.

See salaries and explore the career path for Quantitative Analyst

Business Analyst

Business Analysts help businesses make better decisions by analyzing data and identifying trends. Machine learning is becoming increasingly important in this field, and this course can help you build the skills you need to succeed as a Business Analyst in this new era. You will learn how to build and deploy machine learning models, as well as how to connect your model performance to business metrics.

See salaries and explore the career path for Business Analyst

Product Manager

Product Managers are responsible for the planning, development, and launch of new products. Machine learning is becoming increasingly important in this field, and this course can help you build the skills you need to succeed as a Product Manager in this new era. You will learn how to build and deploy machine learning models, as well as how to connect your model performance to business metrics.

See salaries and explore the career path for Product Manager

Operations Research Analyst

Operations Research Analysts use mathematical and analytical techniques to solve complex business problems. Machine learning becoming increasingly important in this field, and this course can help you build the skills you need to succeed as an Operations Research Analyst in this new era. You will learn how to build and deploy machine learning models, as well as how to connect your model performance to business metrics.

See salaries and explore the career path for Operations Research Analyst

Market Researcher

Market Researchers collect and analyze data about markets and consumers. Machine learning is becoming increasingly important in this field, and this course can help you build the skills you need to succeed as a Market Researcher in this new era. You will learn how to build and deploy machine learning models, as well as how to connect your model performance to business metrics.

See salaries and explore the career path for Market Researcher

Consultant

Consultants help businesses solve problems and improve performance. Machine learning is becoming increasingly important in this field, and this course can help you build the skills you need to succeed as a Consultant in this new era. You will learn how to build and deploy machine learning models, as well as how to connect your model performance to business metrics.

See salaries and explore the career path for Consultant

Statistician

Statisticians collect, analyze, and interpret data. Machine learning is becoming increasingly important in this field, and this course can help you build the skills you need to succeed as a Statistician in this new era. You will learn how to build and deploy machine learning models, as well as how to connect your model performance to business metrics.

See salaries and explore the career path for Statistician

Data Architect

Data Architects design and build data systems. Machine learning is becoming increasingly important in this field, and this course can help you build the skills you need to succeed as a Data Architect in this new era. You will learn how to build and deploy machine learning models, as well as how to connect your model performance to business metrics.

See salaries and explore the career path for Data Architect

Financial Analyst

Financial Analysts use data to make investment decisions. Machine learning is becoming increasingly important in this field, and this course can help you build the skills you need to succeed as a Financial Analyst in this new era. You will learn how to build and deploy machine learning models, as well as how to connect your model performance to business metrics.

See salaries and explore the career path for Financial Analyst

Teacher

Teachers educate students in a variety of subjects. Machine learning is becoming increasingly important in this field, and this course can help you build the skills you need to succeed as a Teacher in this new era. You will learn how to build and deploy machine learning models, as well as how to connect your model performance to business metrics.

See salaries and explore the career path for Teacher

Technical Writer

Technical Writers create documentation for software and other technical products. Machine learning is becoming increasingly important in this field, and this course can help you build the skills you need to succeed as a Technical Writer in this new era. You will learn how to build and deploy machine learning models, as well as how to connect your model performance to business metrics.

See salaries and explore the career path for Technical Writer