Chevron Left
Back to AI Workflow: Machine Learning, Visual Recognition and NLP

Learner Reviews & Feedback for AI Workflow: Machine Learning, Visual Recognition and NLP by IBM

4.4
stars
79 ratings

About the Course

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....

Top reviews

NM

Jul 6, 2020

Dear Team ,

Namaste Everyone !!

Excellent Course structure - ML, VR and NLP.

Great Learning Module Design by All Faculty.

Thanks to everyone!!!

PL

May 2, 2020

The teaching materials are well presented and clear.

Just that the level of this course is a bit not advanced enough.

Filter by:

1 - 13 of 13 Reviews for AI Workflow: Machine Learning, Visual Recognition and NLP

By Neela M

•

Jul 7, 2020

Dear Team ,

Namaste Everyone !!

Excellent Course structure - ML, VR and NLP.

Great Learning Module Design by All Faculty.

Thanks to everyone!!!

By Patrick L

•

May 3, 2020

The teaching materials are well presented and clear.

Just that the level of this course is a bit not advanced enough.

By vignaux

•

Nov 17, 2019

Great course with a lot of practice and smart meaning !

By Julio C

•

Jul 30, 2020

Great training !!!

By Suryabrata D

•

Jul 6, 2020

very Informative

By Takahide M

•

Jan 4, 2023

Very Nice.

By Akarapu K

•

Aug 12, 2024

Very good

By Холмухамедова З Б к

•

May 30, 2022

Perfect

By BHAVANA g

•

Sep 22, 2020

Its pretty difficult to follow up with this course. We must have a good knowledge on Neural n/ws prior starting this course.

By S M A J

•

May 28, 2020

Good for using IBM tools

By Dennis L

•

Aug 29, 2020

Theory Overview only

By David L

•

Aug 26, 2020

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. The video quality was, for the most part, very well done -- but some videos moved too quickly to follow (although it may just be my current level is too low).

I really enjoyed the case studies for the most part; they were challenging and informative, forcing you to learn yourself. There were a couple of areas where I would've appreciated more guidance, such as setting up the MLP/CNN at the end of Week 2. I had no idea that we needed to use a sparse-categorical-crossentropy loss function until I looked at the solution -- and I'm not sure other students would know the same.

Otherwise, it was a useful course.

By Markey S

•

Oct 10, 2024

Too much time on Theory. Little practical work. The practical work is basic and not advanced. Misspellings in Material and Downloads indicate a poor attention to detail from instructors.