Center for Analysis and Design of Intelligent Agents public:t-720-atai:atai-16

public:t-720-atai:atai-16:concepts

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

T-720-ATAI-2016 Lecture Notes, F-1 12.01.2016 What this Course Is / Is not Intelligence This course is about phenomenon we refer to as “intelligence”. A number of features of natural intelligence remain unexplained. AGI A number of terms have been used to refer to the various aspects that people study wrt intelligence. We use the term

public:t-720-atai:atai-16:final_exam_examples

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

Final Exam T-720-ATAI-2016-S Example Questions The final exam will be a 2-hour closed-book exam. Questions will focus on your understanding of the material that has been presented in the course. Below are some example questions. Please note that this is

public:t-720-atai:atai-16:lectures_notes_f-1_12.01.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes, F-1 12.01.2016 What this Course Is / Is not Intelligence This course is about phenomenon we refer to as “intelligence”. A number of features of natural intelligence remain unexplained. AGI A number of terms have been used to refer to the various aspects that people study wrt intelligence. We use the term

public:t-720-atai:atai-16:lectures_notes_f-2_15.01.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes, F-2 15.01.2016 Task-Environments: Key Concepts Task A Problem that can be assigned. Typically comes with Instructions (guide to Solutions). Problem A Goal with (all) relevant constraints (≈ requirements).

public:t-720-atai:atai-16:lecture_notes_f-3_19.01.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes, F-3 19.01.2016 Agents Minimal agent sensory data -> decision -> action Perception Transducer that turns energy into information representation. Decision Computation that uses perceptual data; chooses one alternative over (potentially) many for implementation.

public:t-720-atai:atai-16:lecture_notes_f-4_19.01.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes, F-4 22.01.2016 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-16:lecture_notes_f-4_22.01.2016

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

public:t-720-atai:atai-16:lecture_notes_f-5_26.01.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes F-5 26.01.2016 Why Generality? Breadth of task-environments If a system X can operate in more diverse task-environments than system Y, system X is more flexible than system Y. Breadth of solutions If a system X can reliably generate a larger variation of acceptable solutions to problems than system Y, system X is more

public:t-720-atai:atai-16:lecture_notes_f-6_29.01.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes F-6 29.01.2016 Important Concepts for AGI Attention The management of processing, memory, and sensory resources. Meta-Cognition The ability of a system to reason about itself. Reasoning The application of logical rules to knowledge.

public:t-720-atai:atai-16:lecture_notes_f-7_02.02.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes F-7 02.02.2016 ---------- Systems What Kind of System is Mind? Simple system The human brain consists of 1011 neurons, each with around 1000 connections. A computer has a lot less components, but can hardly be appropriately described as a 'simple system'. Wherever we look, everything points to the mind not being

public:t-720-atai:atai-16:lecture_notes_f-8_05.02.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes F-8 05.02.2016 ---------- Evaluation of Intelligent Systems Sources of Evaluation Methods Psychology Uses tests based on a single measure at a single point in time. Produces a single “IQ” score.

public:t-720-atai:atai-16:lecture_notes_f-9_09.02.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes, F-9 09.02.2016 Requirements for Evaluation: Features That Evaluators Should Be Able To Control Determinism Both full determinism and partial stochasticity (for realism regarding, e.g. noise, stochastic events, etc.) must be supported.

public:t-720-atai:atai-16:lecture_notes_f-10_12.02.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes, F-10 12.02.2016 No lecture notes. In this class we looked at Programming Assignment 3 and discussed Reading Assignment 1.

public:t-720-atai:atai-16:lecture_notes_f-11_16.02.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes, F-11 16.02.2016 Key Features of Feedforward Predictive Control Feedforward Based on correct and accurate predictions, the change of a control signal v can be done before perturbations of v happens, so that the output of the plant o stays constant.

public:t-720-atai:atai-16:lecture_notes_f-12_19.02.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes, F-12 19.02.2016 Constructionist AI What it is Monicker that refers to software development methodologies that require an intelligent designer -- the software programmer as “construction worker”. Why it's important

public:t-720-atai:atai-16:lecture_notes_f-13_23.02.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes, F-12 23.02.2016 Constructionist AI What it is Monicker that refers to software development methodologies that require an intelligent designer -- the software programmer as “construction worker”. Why it's important

public:t-720-atai:atai-16:lecture_notes_f-14_26.02.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes, F-12 26.02.2016 Belusov-Zhaboutinsky Reaction Simulated Belousov-Zhabotinsky Reaction. Source: Wikipedia Belusov-Zhaboutinsky Reaction What it is A chemical reaction discovered in 1950. Why it's important

public:t-720-atai:atai-16:lecture_notes_f-15_01.03.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes, F-12 01.03.2016 Attention the Concept What it is In the domain of intelligent systems the management of system resources is typically called “attention”. Why it's important Any highly capable AI system will need to manage its resources sensibly. In any world (especially the physical world which we inhabit) the availability of content for cognition

public:t-720-atai:atai-16:lecture_notes_f-16_04.03.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes, F-12 04.03.2016 What is Reasoning ? Definition Reasoning is a computation that makes use of given regularities to reach conclusions that have not been stated explicitly. Reasoning is a computation

public:t-720-atai:atai-16:lecture_notes_f-17_08.03.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes, F-12 08.03.2016 Self-Programming What it is Self-programming here means, with respect to some virtual machine M, the production of one or more programs created by M itself, whose principles

public:t-720-atai:atai-16:lecture_notes_f-18_11.03.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes, F-12 11.03.2016 Seed-Based AGI Seed A.k.a. bootstrap code -- the initial knowledge given to a “baby learning machine”. A seed may consist of ontologies, states, models, internal drives, exemplary behaviors and programming skills.

public:t-720-atai:atai-16:lecture_notes_f-19_15.03.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes, F-12 19.03.2016 Creativity & Art What it is The ability of an intelligent system to produce non-obvious solutions to problems. Why it's important Ultimately we want creative machines. Are only artists creative?

public:t-720-atai:atai-16:lecture_notes_f-20_18.03.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes, F-20 18.03.2016 NARS Download Jordi's slides [here], and see reading and study materials here. 2016(c)K. R. Thórisson EOF

public:t-720-atai:atai-16:lecture_notes_f-21_22.03.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes, F-21 22.03.2016 Universal Pedagogy Download Jordi's slides [here], and see reading and study materials here. 2016(c)K. R. Thórisson EOF

public:t-720-atai:atai-16:lecture_notes_f-24_01.04.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes, F-12 01.04.2016 AERA Slides [AERA slides 1. Apr. 2016] 2016(c)Kristinn R. Thórisson EOF

public:t-720-atai:atai-16:lecture_notes_f-25_05.04.2016

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Lecture Notes, F-21 05.04.2016 Download Jordi's slides [here]. 2016(c)K. R. Thórisson EOF

public:t-720-atai:atai-16:main

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

T-720-ATAI, ADVANCED TOPICS IN ARTIFICIAL INTELLIGENCE, SPRING 2016 This Is The Main Page For The Course Instructor: Kristinn R. Thórisson Teaching Assistants: Jordi Bieger (Throstur Thorarensen) 8 ECTS Units, full Master's-level course Days: Tuesdays & Fridays

public:t-720-atai:atai-16:mtalbot-critical-reasoning

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

From Philosophy Now, Issue 106 Critical Reasoning Marianne Talbot Marianne Talbot tells us how to use the ultimate in transferrable skills. My mug is sitting to my right doing nothing. This is because it believes it is at the centre of the universe, and its desire to be at the centre of the universe is stronger than any of its other desires.

public:t-720-atai:atai-16:programming_assignment_1

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Programming Excercise 1 The programming exercises are not meant to train you in reinforcement learning, but rather to highlight some issues of methodology that we believe will play a central role in the rate of advancement in advanced automation. If you think the exercises are too easy it is probably because you are not thinking hard enough. If you think they are too hard please talk to the teacher.

public:t-720-atai:atai-16:programming_assignment_2

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Programming Excercise 2 The programming exercises are not meant to train you in reinforcement learning, but rather to highlight some issues of methodology that we believe will play a central role in the rate of advancement in advanced automation. If you think the exercises are too easy it is probably because you are not thinking hard enough. If you think they are too hard please talk to the teacher.

public:t-720-atai:atai-16:programming_assignment_3

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Programming Excercise 3 The programming exercises are not meant to train you in reinforcement learning, but rather to highlight some issues of methodology that we believe will play a central role in the rate of advancement in advanced automation. If you think the exercises are too easy it is probably because you are not thinking hard enough. If you think they are too hard please talk to the teacher.

public:t-720-atai:atai-16:programming_assignment_4

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Programming Excercise 4 In this exercise you will be getting acquainted with NARS. You should interact with the system as well as place yourself in its shoes. Please don't hesitate to contact us with any questions or problems. [Here] is the PDF for Exercise 4.

public:t-720-atai:atai-16:programming_assignment_5

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Programming Excercise 5 - Final Project In this exercise you will pair up to do some seed programming and teaching to get NARS to perform a range of tasks. Each group will get a different assignment: * Tryggvi and Guðmundur: [Diagnosing, treating and preventing disease]

public:t-720-atai:atai-16:readings

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Readings & Study Material This material is ordered (roughly) by specificity, starting with the general topic of what intelligence is, progressing towards good old-fashioned AI (aka constructionist AI) and then onward towards artificial general intelligence. Within each topic the papers are ordered by importance, the most important first.

public:t-720-atai:atai-16:reading_assignment_1

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Reading Assignment 1 This assignment consist of reading the following paper: * The Physical Symbol System Hypothesis: Status & Prospects by N. J. Nilsson. You must post 2-3 questions on Piazza (make sure you post in the Readingassignments1 thread) that you think are interesting/important/clarifying regarding the paper, and/or that you think the class will learn from addressing during a 30-minute discussion session during class on Friday February…

public:t-720-atai:atai-16:reading_assignment_2

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Reading Assignment 2 This assignment consist of reading the following paper: * Minds Brains & Programs by J. Searle. You must post 2-3 questions on Piazza (make sure you post in the Readingassignments2 thread) that you think are interesting/important/clarifying regarding the paper, and/or that you think the class will learn from addressing during a 30-minute discussion session during class on Friday February 19.

public:t-720-atai:atai-16:reading_assignment_3

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Reading Assignment 3 This assignment consist of reading the following paper: * by D. Chalmers. You must post 2-3 questions on Piazza (make sure you post in the Readingassignments2 thread) that you think are interesting/important/clarifying regarding the paper, and/or that you think the class will learn from addressing during a 30-minute discussion session during class on Friday February 26.

public:t-720-atai:atai-16:reading_assignment_4

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Reading Assignment 4 This assignment consist of reading the following paper: * Every Good Regulator Must be a Good Model by Conant and Ashby. You must post 2-3 questions on Piazza (make sure you post in the Readingassignments2 thread) that you think are interesting/important/clarifying regarding the paper, and/or that you think the class will learn from addressing during a 30-minute discussion session during class on Friday March 4.

public:t-720-atai:atai-16:reading_assignment_5

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

T-720-ATAI-2016 Main T-720-ATAI-2016 Reading Assignment 5 This assignment consist of reading the following paper: * The Singularity: A Reply by D. Chalmers. You must post 2-3 questions on Piazza (make sure you post in the Readingassignments5 thread) that you think are interesting/important/clarifying regarding the paper, and/or that you think the class will learn from addressing during a 30-minute discussion session during class on Friday March 11.

public:t-720-atai:atai-16:short-essay-page

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

Short Essay Pick a topic you think has been neglected in AI research in the past 20 years. Send an email to me (thorisson at gmail.com) with ideas/proposals as soon as possible so that I can help you pick. When a topic has been selected, find 5-7 references relevant to the topic that can help make the argument that the topic has been neglected, and/or provide important context for the topic.