Interpretable machine learning applications: Part 3

Offert par
Coursera Project Network
Dans ce Projet Guidé, vous :

Import, explore and normalize real world data (HELOC) for evaluating the risk performance of mortgage applications

Train and test a prediction model as a Sequential model based Artificial Neural Network (ANN)

Generate explanations based on profiles of mortgage applicants closest to the individual requesting the explanation.

Clock2 hours
IntermediateIntermédiaire
CloudAucun téléchargement requis
VideoVidéo en écran partagé
Comment DotsAnglais
LaptopOrdinateur de bureau uniquement

In this 50 minutes long project-based course, you will learn how to apply a specific explanation technique and algorithm for predictions (classifications) being made by inherently complex machine learning models such as artificial neural networks. The explanation technique and algorithm is based on the retrieval of similar cases with those individuals for which we wish to provide explanations. Since this explanation technique is model agnostic and treats the predictions model as a 'black-box', the guided project can be useful for decision makers within business environments, e.g., loan officers at a bank, and public organizations interested in using trusted machine learning applications for automating, or informing, decision making processes. The main learning objectives are as follows: Learning objective 1: You will be able to define, train and evaluate an artificial neural network (Sequential model) based classifier  by using keras as API for TensorFlow. The pediction model will be trained and tested with the HELOC dataset for approved and rejected mortgage applications. Learning objective 2: You will be able to generate explanations based on similar profiles for a mortgage applicant predicted either as of "Good" or "Bad" risk performance. Learning objective 3: you will be able to generate contrastive explanations based on feature and pertinent negative values, i.e., what an applicant should change in order to turn a "rejected" application to an "approved" one.

Les compétences que vous développerez

  • Training and testing an Artificial Neural Network
  • Using the Protodash algorithm
  • Using keras as API for TensorFlow
  • Normalization of data prior to training a prediction model
  • Explanations based on similarity measurements

Apprendrez étape par étape

Votre enseignant(e) vous guidera étape par étape, grâce à une vidéo en écran partagé sur votre espace de travail :

  1. By the end of task 1, you will be able, as a data scientist or loan officer persona, to load, process and normalize the (HELOC) dataset about mortgage applications for training purposes.

  2. By the end of task 2, you will be able to define, train and evaluate an artificial neural network based classifier  by using TensorFlow.

  3. By the end of tasks 3 and 4, you will be able to obtain similar samples as explanations for a mortgage applicant predicted as "Good" and "Bad", respectively.

  4. By the end of task 5, you will be able to provide contrastive explanations for decisions affecting individual cases.

Comment fonctionnent les Projets Guidés

Votre espace de travail est un bureau cloud situé dans votre navigateur, aucun téléchargement n'est requis.

Votre enseignant(e) vous guide étape par étape dans une vidéo en écran partagé

Foire Aux Questions

Foire Aux Questions

D'autres questions ? Visitez le Centre d'Aide pour les Étudiants.