Center for Analysis and Design of Intelligent Agents public:t-720-atai:atai-21

public:t-720-atai:atai-21:agents_and_control

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

T-720-ATAI-2021 Main Links to Lecture Notes CONTROL What is a Controller? Abstract Controller An abstraction of a controller: A set of processes P that can receive an input, i_t~in~I, produced by and selected from a task-environment, current state S, at least one goal G (implicit or explicit - see table below) and output o_t~in~O in the form of atomic actions (selected from a set of atomic possible outputs O), that (in the lim…

public:t-720-atai:atai-21:ai_architectures

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

T-720-ATAI-2021 Main Links to Lecture Notes SYMBOLS, MODELS, CAUSALITY: AI Architectures Refresher: System Architecture What it is In CS: the organization of the software that implements a system. In AI: The total system that has direct and independent control of the behavior of an Agent via its sensors and effectors.

public:t-720-atai:atai-21:engineering_assignment_1

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

T-720-ATAI-2021 Main ATAI-21 Reykjavik University Engineering Assignment 1: Learning Aim: This assignment is meant to give you a better insight into deep reinforcement learning and its difference to cumulative and life-long learning on the example of human learning.

public:t-720-atai:atai-21:engineering_assignment_2

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

ATAI-21 Main ATAI-21 Reykjavik University Engineering Assignment 2: Non-Axiomatic Reasoning System (NARS) and OpenNARS for Applications (ONA) Aim: This assignment is meant to introduce you to OpenNARS-for-Applications (ONA), a general machine intelligence (GMI) aspiring system created by Patrick Hammer which is derived from Pei Wang’s Non-Axiomatic Reasoning System (NARS).

public:t-720-atai:atai-21:evaluation

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

T-720-ATAI-2021 Main Learning / Evaluation Evaluation of Intelligent Systems The Challenge of Evaluating Intelligence Without Evaluation... ...there can be no comparison. Without comparison there can be no indication of direction. Without direction there can be no systematic scientific (or otherwise) effort to deepen understanding.

public:t-720-atai:atai-21:example_questions_2021

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

Final Exam T-720-ATAI-2021 The final exam will be a 3-hour open-book on-line exam (Canvas). Questions will focus on your understanding of the material that has been presented in the course and can be found in the assigned readings and lecture notes, with an emphasis on the main concepts and topics and your ability to holistically comprehend these.

public:t-720-atai:atai-21:final_project

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

ATAI-21 Main ATAI-21 Reykjavik University Final Project Description For the final project you are asked to implement your own original task into the TestChamber (see linkg to the Introduction for the Final Project below), implemented by you and your collborator.

public:t-720-atai:atai-21:final_project_intro

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

T-720-ATAI-2021 Main ATAI-21 Reykjavik University Final Project: Preparations Summary: In the final project you will be working with OpenNARS for Research (a different version than ONA - OpenNARS for Applications), with the main purpose of doing AGI research using NARS. To help you get going with it, OpenNARS for Research comes with libraries of various examples of usage, including a graphical user interface for interacting with it. OpenNARS for Research is written in Java.

public:t-720-atai:atai-21:generality

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

T-720-ATAI-2021 Main Links to Lecture Notes CONTROL: Intelligence & Generality Generality What Do You Mean by "Generality"? Flexibility: Breadth of task-environments Enumeration of variety. (By 'variety' we mean the discernibly different states that can be sensed and that make a difference to a controller.)

public:t-720-atai:atai-21:how_to_write_good_abstracts

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

T-720-ATAI-2021: 'Mock' Abstracts & 'Final' Abstracts What Are Abstracts Good For? Purpose The purpose of writing an abstract for a scientific paper is to serve as a guide to your readers. What an abstract should say Having read a paper's title and the abstract, a reader should have a

public:t-720-atai:atai-21:intelligence

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

T-720-ATAI-2021 Main Links to Lecture Notes INTELLIGENCE Intelligence: A Natural Phenomenon Intelligence Phenomenon. Intelligence is a phenomenon with good examples in the natural world, but may have more forms than the examples from nature. The only one that everyone agrees on to call 'intelligent':

public:t-720-atai:atai-21:learning

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

T-720-ATAI-2021 Main Learning Terminology & Definitions Key Learning Terms What it is Learning is a process that has the intent of acquiring actionable information, a.k.a. knowledge. Key Features Inherits key features of any process: -

public:t-720-atai:atai-21:learning_outcomes

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

DCS-T-720-ATAI-2021 Main Learning Outcomes DCS-t-720-ATAI-21 English After taking the course, diligently attending the classes and doing the assignments, thoroughly reading, and actively participating in discussions, students should be able to: * Identify key challenging research questions related to advanced machine learning and (AML) artificial general intelligence (AGI)

public:t-720-atai:atai-21:lecture_notes

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

T-720-ATAI-2021 Main T-720-ATAI-2021 Links to Thorisson's Lecture Notes * W1: INTRODUCTION * Intelligence: The Phenomenon * Sprint W2+W3: WORLDS * Key concepts: Environment, tasks, entities, variables, tests, goals, behaviors * Tasks & Environments * Emergence & Self-Organization (not mandatory) * Sprint W4+W5: LEARNING

public:t-720-atai:atai-21:main

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

T-720-ATAI, ADVANCED TOPICS IN ARTIFICIAL INTELLIGENCE, Fall 2021 —Second Year of COVID— OVERVIEW See last year's course here See Canvas For Up-To-Date Information, Notifications, Links to Lecture Notes Instructor: Kristinn R. Thórisson Teaching Assistants: Arash Sheikhlar, Leonard Eberding

public:t-720-atai:atai-21:methodologies

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

T-720-ATAI-2021 Main Links to Lecture Notes UNDERSTANDING: Methodologies Methodology What It a Methodology? What it is The methods - tools and techniques - we use to study a phenomenon. Examples - Comparative experiments (for the answers we want Nature to ultimately give).

public:t-720-atai:atai-21:readings

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

DCS-T-720-ATAI-2021 Main T-720-ATAI-2021 Readings & Study Material Readings README (Do not skip!) INTELLIGENCE: THE PHENOMENON The Human Animal [ 9,10 ] What is intelligence? How do experts talk about it? What has been uncovered? What uniquely separates the phenomenon of intelligence from other similar phenomena in the world?

public:t-720-atai:atai-21:self-organization

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

Complexity & Emergence Examples of Self-Organization (Emergence) Group Clapping Try this in class: Start clapping; aim for clapping at the same rate as everyone else in the room. Self-organization without centralized control. Conway's Game of Life

public:t-720-atai:atai-21:self-x

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

T-720-ATAI-2021 Main Links to Lecture Notes CONTROL: Self-X, Predictability & Reliability Autonomy What It Is Autonomy is a key feature of intelligence - the ability of a system to “act on its own”. Autonomous-X is anything that “autonomy” is relevant for or applies to in a system's operation.

public:t-720-atai:atai-21:short_essay_topics

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

DCS-T-720-ATAI-2021 Main T-720-ATAI-2021 Short Essay: Selected Topics How to Write Good Abstracts * Agnar * Are We Having Too Much Influence on AI When Designing It? * Birgir * TBD * Chloe * High-Level Dispatching of Low-Level Jobs * Fjölnir * Why Must a General Learner be a Heuristics Factory?

public:t-720-atai:atai-21:task-environment

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

T-720-ATAI-2021 Main WORLDS "The World" What is it? A set of constraints on what is and isn't possible. We perceive the physical world through sensors. Sensors are physical Our sensors are made from the same stuff that they perceive. Descartes René Descartes, the French philosopher, famously claimed that

public:t-720-atai:atai-21:teaching

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

T-720-ATAI-2021 Main T-720-ATAI-2021 Learning / Teaching The Pedagogical Pentagon: A Framework for (Artificial) Pedagogy What is Needed We need a universal theory of learning -- and in fact of teaching, training, task-environments, and evaluation. Anything short of having complete theories for all of these means that experimentation, exploration, and blind search are the only ways to answer questions about performance, curriculum design, training requirements, etc., from which …

public:t-720-atai:atai-21:understanding

Anonymous (anonymous@undisclosed.example.com) — 2024-04-29T13:33:28+00:00

T-720-ATAI-2021 Main Links to Lecture Notes UNDERSTANDING: Understanding, Curiosity, Creativity Curiosity What is Curiosity? What It Is The tendency of a learner to seek out novel inputs that may not have any relevance to its currently active goals. Why It Matters