ML/DL Best Practices: Machine Learning Workflow Best Practices

Machine Learning    |    Intermediate
  • 12 videos | 52m 8s
  • Includes Assessment
  • Earns a Badge
Rating 4.5 of 8 users Rating 4.5 of 8 users (8)
This 12-video course explores essential phases of machine learning (ML), deep learning workflows, and data workflows that can be used to develop ML models. You will learn the best practices to build robust ML systems, and examine the challenges of debugging models. Begin the course by learning the importance of the data structure for ML accuracy and feature extraction that is wanted from the data. Next, you will learn to use checklists to develop and implement end-to-end ML and deep learning workflows and models. Learners will explore what factors to consider when debugging, and how to use flip points to debug a trained machine model. You will learn to identify and fix issues associated with training, generalizing, and optimizing ML models. This course demonstrates how to use the various phases of machine learning and data workflows that can be used to achieve key milestones of machine learning projects. Finally, you will learn high level-deep learning strategies, and the common design choices for implementing deep learning projects.

WHAT YOU WILL LEARN

  • Discover the key concepts covered in this course
    List the various phases of machine learning workflow that can be used to achieve key milestones of machine learning projects
    Recall the data workflows that are used to develop machine learning models
    Identify the differences between machine learning and deep learning and illustrate the phases of deep learning workflow
    List the best practices that should be adopted to build robust machine learning systems, with focus on the evaluation approach
    Recall the challenges of debugging machine learning and deep learning projects and the factors that need to be considered while debugging
  • Describe the approach of debugging trained machine learning models using flippoints
    Recognize the benefits of implementing machine learning checklists and the process of building checklists that can be used to work through applied machine learning problems
    Describe checklists for debugging neural networks, the steps involved in identifying and fixing issues associated with training, and generalizing and optimizing machine learning models
    Recall the checklists for implementing end-to-end machine learning and deep learning workflows that should be adopted to build optimized machine learning and deep learning models
    Describe the high-level deep learning strategies and the common design choices for implementing deep learning projects
    Summarize the key concepts covered in this course

IN THIS COURSE

  • 1m 11s
  • 7m 13s
    Upon completion of this video, you will be able to list the various phases of the machine learning workflow that can be used to achieve key milestones of machine learning projects. FREE ACCESS
  • Locked
    3.  Data Workflows for Machine Learning
    5m 42s
    After completing this video, you will be able to recall the data workflows that are used to develop machine learning models. FREE ACCESS
  • Locked
    4.  Phases of Deep Learning Flow
    7m 30s
    In this video, you will identify the differences between machine learning and deep learning, and illustrate the phases of the deep learning workflow. FREE ACCESS
  • Locked
    5.  Machine Learning Evaluation Approach
    5m 33s
    Upon completion of this video, you will be able to list the best practices that should be adopted to build robust machine learning systems, with a focus on the evaluation approach. FREE ACCESS
  • Locked
    6.  Challenges of Debugging Machine Learning
    4m
    Upon completion of this video, you will be able to recall the challenges of debugging machine learning and deep learning projects and the factors that need to be considered while debugging. FREE ACCESS
  • Locked
    7.  Debugging Trained ML Models Using Flippoints
    3m 50s
    After completing this video, you will be able to describe the approach of debugging trained machine learning models using breakpoints. FREE ACCESS
  • Locked
    8.  Benefits of Machine Learning Checklists
    5m 45s
    Upon completion of this video, you will be able to recognize the benefits of implementing machine learning checklists and the process of building checklists that can be used to work through applied machine learning problems. FREE ACCESS
  • Locked
    9.  Checklists for Debugging Neural Network
    2m 48s
    Upon completion of this video, you will be able to describe checklists for debugging neural networks, the steps involved in identifying and fixing issues associated with training, and generalizing and optimizing machine learning models. FREE ACCESS
  • Locked
    10.  Machine Learning End-to-End Workflow Checklists
    3m 32s
    Upon completion of this video, you will be able to recall the checklists for implementing end-to-end machine learning and deep learning workflows. These checklists should be adopted to build optimized machine learning and deep learning models. FREE ACCESS
  • Locked
    11.  Learning Strategy and Design Choices
    3m 22s
    Upon completion of this video, you will be able to describe high-level deep learning strategies and common design choices for implementing deep learning projects. FREE ACCESS
  • Locked
    12.  Course Summary
    1m 42s

EARN A DIGITAL BADGE WHEN YOU COMPLETE THIS COURSE

Skillsoft is providing you the opportunity to earn a digital badge upon successful completion on some of our courses, which can be shared on any social network or business platform.

Digital badges are yours to keep, forever.

YOU MIGHT ALSO LIKE

Course Machine Learning with BigQuery ML: Building Unsupervised Models
Rating 4.3 of 3 users Rating 4.3 of 3 users (3)
Course Fundamentals of AI & ML: Advanced Data Science Methods
Rating 4.4 of 136 users Rating 4.4 of 136 users (136)
Course MLOps with MLflow: Getting Started
Rating 5.0 of 1 users Rating 5.0 of 1 users (1)

PEOPLE WHO VIEWED THIS ALSO VIEWED THESE

Course ML/DL in the Enterprise: Machine Learning Modeling, Development, & Deployment
Rating 4.4 of 34 users Rating 4.4 of 34 users (34)
Course Research Topics in ML & DL
Rating 4.3 of 16 users Rating 4.3 of 16 users (16)
Course Refactoring ML/DL Algorithms: Refactor Machine Learning Algorithms
Rating 4.5 of 40 users Rating 4.5 of 40 users (40)