3) Responsible Artificial Intelligence Practices (P2) Flashcards
(21 cards)
Transparent and Explainable Models: Transparency:
Answers the question HOW a model makes decisions.This helps to provide accountability and builds trust in the AI system. Transparency also makes auditing a system easier.
Transparent and Explainable Models: Explainability:
helps to understand WHY the model made the decision that it made. It gives insight into the limitations of a model.This helps developers with debugging and troubleshooting the model. It also allows users to make informed decisions on how to use the model.
black box models:
Models that lack transparency and explainability are often referred to as black box models. These models use complex algorithms and numerous layers of neural networks to make predictions, but they do not provide insight into their internal workings.
Solutions for transparent and explainable models:
-Explainability frameworks
-Transparent documentation
-Monitoring and auditing
-Human oversight and involvement
-counterfactual explanations
-UI explanations
Risks of transparent and explainable models:
-Increasing the complexity of the development and maintenance of the model can increase the costs.
-Creating vulnerabilities of the model, data, and algorithms can be exploited by bad actors.
-Presenting unrealistic expectations that the model is perfectly transparent and explainable.
-Providing too much information that can create privacy and security concerns.
AWS tools for transparency: AI Service Cards:
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.
AWS tools for transparency: SageMaker Model Cards:
document critical details about your ML models in a single place for streamlined governance and reporting.document critical details about your ML models in a single place for streamlined governance and reporting.
AWS tools for explainability: SageMaker Clarify:
provide scores detailing which features contributed the most to your model prediction on a particular input for tabular, NLP, and computer vision models.
AWS tools for explainability: SageMaker Autopilot:
help provide insights into how ML models make predictions. These tools can help ML engineers, product managers, and other internal stakeholders understand model characteristics.
Performance and interpretability Trade-Offs:
If a business wants high model transparency and wants to understand exactly why and how the model is generating predictions, then they need a model that offers interpretability. However, high interpretability typically comes at the cost of performance
Interpretability
Interpretability is the access into a system so that a human can interpret the model’s output based on the weights and features.
Explainability
Explainability is how to take an ML model and explain the behavior in human terms.
Safety and transparency trade-offs:
model safety focuses on protecting information and model transparency focusing on exposing information, hence there is a trade-off while trying to achieve balance
Model controllability:
A controllable model is one where 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.
Principles of Human-Centered Design for Explainable AI
Human-centered design (HCD) is 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.
Human-centered design Principles
Design for amplified decision-making,
Design for unbiased decision-making,
Design for human and AI learning.
Design for amplified decision-making:
The principle of design for amplified decision-making supports decision-makers in high-stakes situations.
Key aspects: Clarity,Simplicity,Usability,Reflexivity,Accountability
Design for unbiased decision-making:
The design for unbiased decision-making principle and practices aim to ensure that the design of decision-making processes, systems, and tools is free from biases that can influence the outcomes.
Key aspects: Transparency,Fairness,Training
Design for human and AI learning:
Design for human and AI learning is a process that aims to create learning environments and tools that are beneficial and effective for both humans and AI.
Key aspects: Cognitive apprenticeship,Personalization,User-centered design
Reinforcement learning from human feedback:
ML technique that uses human feedback to optimize ML models to self-learn more efficiently. Reinforcement learning (RL) techniques train software to make decisions that maximize rewards, which makes their outcomes more accurate.
Benefits of RLHF:Enhances AI performance,Supplies complex training parameters,Increases user satisfaction
Amazon SageMaker Ground Truth
SageMaker Ground Truth 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.
