Advanced Functionality of Microsoft Cognitive Toolkit (CNTK)


Overview/Description
Expected Duration
Lesson Objectives
Course Number
Expertise Level



Overview/Description

Microsoft Cognitive Toolkit provides powerful machine learning and deep learning algorithms for developing AI. Knowing which problems are easier to solve using Microsoft CNTK over other frameworks helps AI practitioners decide on the best software stack for a given application.

In this course, you'll explore advanced techniques for working with Microsoft CNTK and identify which cases benefit most from MS CNTK. You'll examine how to load and use external data using CNTK and how to use its imperative and declarative APIs. You'll recognize how to carry out common AI development tasks using CNTK, such as working with epochs and batch sizes, model serialization, model visualization, feedforward neural networks, and machine learning model evaluation.

Finally, you'll implement a series of practical AI projects using Python and MS CNTK.



Expected Duration (hours)
0.8

Lesson Objectives

Advanced Functionality of Microsoft Cognitive Toolkit (CNTK)

  • discover the key concepts covered in this course
  • specify cases in which it's advantageous to use CNTK over other platforms
  • describe how to load and use external data using Microsoft CNTK
  • outline the CNTK training process when called with an imperative API
  • outline the CNTK training process when called with a declarative API
  • define epochs and batch sizes in CNTK and specify how to choose the optimal values for best performance
  • recognize the model serialization process using CNTK
  • identify how CNTK can be used for model visualization
  • use CNTK to create and train a feedforward neural network and demonstrate its performance
  • work with CNTK evaluation tools to evaluate previously created CNTK machine learning models
  • use Python to apply pre-processing techniques to diabetic patients' data and use this data to troubleshoot the creation and training of CNTK machine learning classification models
  • use Python to apply pre-processing techniques to credit rating data and use this data to troubleshoot the creation and training of CNTK machine learning regression models
  • utilize Python to apply pre-processing techniques to housing price data and use this data to troubleshoot the creation and training of CNTK machine learning regression models
  • " utilize Python to apply pre-processing techniques to professional salary data and use this data to troubleshoot the creation and training of CNTK machine learning classification models "
  • summarize the key concepts covered in this course
  • Course Number:
    it_aiexmsdj_01_enus

    Expertise Level
    Expert