Displaying 11 resources
Online Course Online Course

Non-Markov Decision Processes and Reinforcement Learning

We present non-Markov decision processes, where rewards and dynamics can depend on the history of events. This is contrast with Markov Decision Processes, where the dependency is limited to the last state and action.

Category
Hybrid Decision Making
Target audience
ADR Experts and Associations, Researchers and Academic
Source
Adra-e
Tutorial/How To/Guides Tutorial/How To/Guides

Algorithmic Impact Assessment tool

The Algorithmic Impact Assessment (AIA) is a mandatory risk assessment tool intended to support the Treasury Board’s Directive on Automated Decision-Making.

Category
Trustworthiness
Target audience
Public Sector
Source
Adra-e
Video/Webinars Video/Webinars

SAFEXPLAIN Introduction to Trustworthy AI for Safety-Critical Systems

This introductory video provides an overview of the steps taken by the SAFEXPLAIN project to ensure that the AI-based solutions used in safety-critical systems are Trustworthy, explainable and comply with the safety guidelines of diverse industria

Category
Data flow standards, Certification and Compliance, Trustworthiness
Target audience
Individual Citizens/Members of the Society, Policy Makers, Private Sector
Source
Adra-e
Certification Certification

ALIGNER Fundamental Rights Impact Assessment

Artificial intelligence can enhance law enforcement agencies’ capabilities to prevent, investigate, detect and prosecute crimes, as well as to predict and anticipate them.

Category
Action and Interaction Technologies, Edge-based AI, Multi-modal interaction, Real-time context aware decision making, Semantic knowledge, Sensing of motion and mechanical properties, Fundamental Rights, Principles, and Values, Multistakeholder dialogue, Understanding of the fundamental rights and values, Policy, Regulation, Certificates, and Standards, Best practices in deployment, Certification and Compliance, Legal framework and regulation, Reasoning and decision-making Technologies, Hybrid Decision Making, Reasoning Techniques, Trustworthiness, Sensing and perception technologies, Architecture of sensing and perception systems, Meta-data contexts, Sensing and processing methods, Systems, methodologies, hardware, and tools, Support tools, System architectures, Technology methodologies and landscape
Target audience
Public Sector
Source
Adra-e
White paper White paper

A General Language Assistant as a Laboratory for Alignment

Given the broad capabilities of large language models, it should be possible to work towards a general-purpose, text-based assistant that is aligned with human values, meaning that it is helpful, honest, and harmless.

Category
Trustworthiness
Source
Adra-e