Responsible AI Practices

Question 1

Data Bias

Answer 1

If the training data used to train an AI model is biased or underrepresents certain groups, the resulting model may exhibit biases in its predictions or decisions.

Question 2

Explainability

Answer 2

Answers the question WHY. Explainability refers to the characteristic of an AI model to clearly explain or provide justification for its internal mechanisms and decisions so that it is understandable to humans.

Question 2

Interaction bias

Answer 2

Biases can also arise from the way humans interact with AI systems or the context in which the AI is deployed. For example, if an AI system for facial recognition is primarily tested on a certain demographic group, it may perform poorly on other groups.

Question 3

Algorithm bias

Answer 3

The algorithms and models used in AI systems can introduce biases, even if the training data is unbiased. This can happen due to the inherent assumptions or simplifications made by the algorithms

Question 4

Transparency

Answer 4

Answers the question HOW. The practice of how you might communicate information about an AI system. Some of this information includes development processes, system capabilities, and limitations.

Question 5

Veracity and robustness

Answer 5

Veracity and robustness in AI refers to the mechanisms to ensure an AI system operates reliably, even with unexpected situations, uncertainty, and errors

Question 6

Governance

Answer 6

The governance dimension refers to the set of processes that are used to define, implement, and enforce responsible AI practices within an organization.

Question 7

Safety

Answer 7

Safety in responsible AI refers to the development of algorithms, models, and systems in such a way that they are responsible, safe, and beneficial for individuals and society as a whole

Question 8

Controllability

Answer 8

The controllability dimension in responsible AI refers to a framework for how you might monitor and guide an AI system’s behavior to align with human values and intent

Question 9

Amazon Bedrock

Answer 9

Fully managed service that makes available high-performing FMs from leading AI startups and Amazon for your use through a unified API. You can choose from a wide range of FMs to find the model that is best suited for your use case. Amazon Bedrock also offers a broad set of capabilities to build generative AI applications with security, privacy, and responsible AI.

Question 10

Amazon SageMaker Model Monitor

Answer 10

monitors the quality of SageMaker machine learning models in production. You can set up continuous monitoring with a real-time endpoint (or a batch transform job that runs regularly), or on-schedule monitoring for asynchronous batch transform jobs

Question 11

Amazon Augmented AI (Amazon A2I)

Answer 11

a service that helps build the workflows required for human review of ML predictions

Question 12

Amazon tools that can be used to balance your dataset

Answer 12

SageMaker Clarify and SageMaker Data Wrangler

Question 13

What is curating a dataset?

Answer 13

Curating datasets is the process of labeling, organizing, and preprocessing the data so that it can perform accurately on the model

Question 14

What is data preprocessing?

Answer 14

Preprocess the data to ensure it is accurate, complete, and unbiased. Techniques such as data cleaning, normalization, and feature selection can help to eliminate biases in the dataset.

Question 15

What is data augmentation?

Answer 15

Use data augmentation techniques to generate new instances of underrepresented groups. This can help to balance the dataset and prevent biases towards more represented groups.

Question 16

SageMaker Clarify

Answer 16

provides purpose-built tools to gain greater insights into ML models and data based on metrics such as accuracy, robustness, toxicity, and bias to improve model quality and support responsible AI initiatives.

Question 17

AI Service Cards

Answer 17

form of documentation on responsible AI. They provide teams with a single place to find information on the intended use cases and limitations, responsible AI design choices, and deployment and performance optimization best practices for AWS AI services.

Question 18

Which 2 AWS services or features help with monitoring and human review

Answer 18

1) Amazon SageMaker Model Monitor & 2) Amazon Augmented AI (Amazon A2I)

Question 19

AWS services for finding the best model

Answer 19

Model evaluation on Amazon bedrock

Question 20

AWS model for guarding against harmful content

Answer 20

Guardrails for Amazon Bedrock

Question 21

Name some explainability frameworks

Answer 21

1) SHapley Value Added (SHAP) 2) Local Interpretable Model-Agnostic Explanations (LIME) 3)Counterfactual Explanations

Question 22

AWS AI Service Cards

Answer 22

AI service cards are a form of responsible AI documentation that provides customers with a single place to find information on the intended use cases and limitations, responsible AI design choices, and the deployment and operation best practices for our AI services. These are not customizable.

Question 23

Amazon Safe Maker Model Cards

Answer 23

Use to document critical details about your ML models in a single place for streamlined governance and reporting.

Question 24

Overfitting

Answer 24

(bias is low and the variance is high.) when model performs well on the training data but does not perform well on the evaluation data.

Question 25

Cross validation

Answer 25

a technique for evaluating ML models by training several ML models on subsets of the available input data and evaluating them on the complementary subset of the data. Cross-validation should be used to detect overfitting.

Question 26

Regularization

Answer 26

a method that penalizes extreme weight values to help prevent linear models from overfitting training data examples.

Question 27

Dimension reduction

Answer 27

an unsupervised machine learning algorithm that attempts to reduce the dimensionality (number of features) within a dataset while still retaining as much information as possible.

Question 28

Interpretability

Answer 28

the degree to which a human can understand the cause of a decision.

Interpretability is the access into a system so that a human can interpret the model’s output based on the weights and features.

Question 29

Model safety

Answer 29

the ability of an AI system to avoid causing harm in its interactions with the world. This includes avoiding social harm, such as bias in decision-making algorithms, and avoiding privacy and security vulnerability exposures.

Question 30

Model control

Answer 30

You can influence the model’s predictions and behavior by changing aspects of the training data. Higher controllability provides more transparency into the model and allows correcting undesired biases and outputs.

Model controllability is measured by how much control you have over the model by changing the input data.

Question 31

HCD (Human Centered Design)

Answer 31

an approach to creating products and services that are intuitive, easy to use, and meet the needs of the people who will be using them.

Question 32

3 key principles of human centered design for explainable AI

Answer 32

Design for amplified decision-making.

Design for unbiased decision-making.

Design for human and AI learning.

Question 33

Reflexivity

Answer 33

An aspect of design for amplified decision making; its designing technology that prompts users to reflect on their decision-making process and encourages them to take responsibility for their choices.

Question 34

3 aspects of unbiased decision making

Answer 34

Identify and assess potential biases.

Design decision-making processes and tools that are transparent and fair.

Train decision-makers to recognize and mitigate biases.

Question 35

Key aspects for designing for human and AI learning

Answer 35

1) Cognitive apprenticeship (creating learning environments where AI systems learn from human instructors)
2) Personalization (tailor-making learning experiences and tools)
3) User-centered design (designing learning environments and tools that are intuitive and accessible to different types of learners)

Question 36

SageMaker Ground Truth

Answer 36

offers the most comprehensive set of human-in-the-loop capabilities for incorporating human feedback across the ML lifecycle to improve model accuracy and relevancy

Question 37

Which AWS solution should the developer consider to increase the explainability of their system?

Answer 37

SageMaker Autopilot to provide explainable insights into how ML models make predictions.

Question 38

Interpretability

Answer 38

A model that provides transparency into a system so a human can explain the model’s output based on the weights and features is an example of interpretability in a model.

Question 38

Controllability in a model

Answer 38

A model that you can influence the predictions and behavior by changing aspects of the training data