Course details

Improving Neural Networks: Neural Network Performance Management

Improving Neural Networks: Neural Network Performance Management


Overview/Description
Expected Duration
Lesson Objectives
Course Number
Expertise Level



Overview/Description

In this 12-video course, learners can explore machine learning problems that can be addressed with hyperparameters, and prominent hyperparameter tuning methods, along with problems associated with hyperparameter optimization. Key concepts covered here include the iterative workflow for machine learning problems, with a focus on essential measures and evaluation protocols; steps to improve performance of neural networks, along with impacts of data set sizes on neural network models and performance estimates; and impact of the size of training data sets on quality of mapping function and estimated performance of a fit neural network model. Next, you will learn the approaches of identifying overfitting scenarios and preventing overfitting by using regularization techniques; learn the impact of bias and variances on machine learning algorithms, and recall the approaches of fixing high bias and high variance in data sets; and see how to trade off bias variance by building and deriving an ideal learning curve by using Python. Finally, learners will observe how to test multiple models and select the right model by using Scikit-learn.



Expected Duration (hours)
2.0

Lesson Objectives

Improving Neural Networks: Neural Network Performance Management

  • discover the key concepts covered in this course
  • describe the iterative workflow for machine learning problems with focus on essential measures and evaluation protocols
  • recognize the machine learning problems that can be addressed using hyperparameters along with the various hyperparameter tuning methods and the problems associated with hyperparameter optimization
  • recall the steps to improve the performances of neural networks along with impact of dataset sizes on neural network models and performance estimates
  • demonstrate the impact of the size of training dataset on the quality of mapping function and the estimated performance of a fit neural network model
  • recall the approaches of identifying overfitting scenarios and preventing overfitting using regularization techniques
  • recognize the critical problems associated with neural networks along with the essential approaches of resolving them
  • describe the impact of bias and variances on machine learning algorithms and recall the approaches of fixing high bias and high variance in data sets
  • demonstrate how to trade off bias variance by building and deriving an ideal learning curve using Python
  • recognize the various approaches of improving the performance of machine learning using data, algorithm, algorithm tuning and ensembles
  • demonstrate how to test multiple models and select the right model using Scikit-learn
  • specify the machine learning problems that we can address using hyperparameters, describe the impact of bias and variances on machine learning algorithms and test multiple models using Scikit-learn
  • Course Number:
    it_mlinnrdj_01_enus

    Expertise Level
    Intermediate