/awesome-agi-cocosci

An awesome & curated list for Artificial General Intelligence, an emerging inter-discipline field that combines artificial intelligence and computational cognitive sciences.

Primary LanguageTeXCreative Commons Zero v1.0 UniversalCC0-1.0

Roadmap of studying Abduction

Awesome Artificial General Intelligence and Computational Cognitive Sciences Awesome

An awesome & curated list for Artificial General Intelligence, an emerging inter-discipline field that combines artificial intelligence and computational cognitive sciences as majority, alone with probability and statistics, formal logic, cognitive and developmental psychology, computational philosophy, cognitive neuroscience, and computational sociology. We are promoting high-level machine intelligence by getting inspirations from the way that human learns and thinks, while obtaining a deeper understanding of human cognition simultaneously. We believe that this kind of reciprocative research is a potential way towards our big picture: building human-level intelligent systems with capabilities such as abstracting, explaining, learning, planning, and making decisions. And such intelligence may generally help people improve scientific research, engineering, and the arts, which are the hallmarks of human intelligence.

Awesome AGI & CoCoSci is an all-in-one collection, consisting of recources from basic courses and tutorials, to papers and books around diverse topics in mutiple perspectives. Both junior and senior researchers, whether learning, working on, or working around AGI and CoCoSci, meet their interest here.

Contributing

Contributions are greatly welcomed! Please refer to Contribution Guidelines before taking any action.

Contents

Academic Tools

Courses

*Back to Top

Programming

  • Probabilistic Models of Cognition - MIT. The probabilistic approach to cognitive science, which models learning and reasoning as inference in complex probabilistic models.

*Back to Top

Paper Writing

  • LaTex Configuration - LaTex. LaTex template for configuration file with elegant reference style (gray-colored reference, page backward reference).

  • BibTex Template - BibTex. BibTex template for including abbreviations of journals and conferences in AI, Mathematics, and Cognitive Sciences.

  • bioRender - bioRender. Create professional science figures in minutes by browsing thousands of pre-made icons and templates from more than 30 fields of life sciences.

  • How to construct a Nature summary paragraph - Nature. Nature official guidelines for composing abstracts.

  • How to write a superb literature review - Nature, 2020. Nature speaks to old hands and first timers about the work they did to make their reviews sing.

  • Scientific Papers - Nature. Nature guidance on writing scientific papers.

  • The Machine Learning Reproducibility Checklist - McGill University. Guidelines for introducing a machine learning algorithm with guarantee of reproducibility.

*Back to Top

Paper Reading

*Back to Top

Literature Management

*Back to Top

Knowledge Management

*Back to Top

Papers

Abduction

Explanation

*Back to Top

Scientific Discovery

*Back to Top

Rationalization

*Back to Top

Applications in AI

*Back to Top

Bayesian Modeling

Bayesian Induction

*Back to Top

Generative Model

*Back to Top

Nonparametric Model

*Back to Top

Bayesian Optimization

*Back to Top

Concepts

Theory of Concepts

*Back to Top

Human Concept Representation

*Back to Top

AI Concept Representation

*Back to Top

Complexity & Information Theory

Theory

*Back to Top

Dimensionality Reduction

*Back to Top

Visual Complexity

*Back to Top

Communications

Non-Verbal Communication

*Back to Top

Pragmatics

*Back to Top

Language Compositionality

*Back to Top

Coordination

*Back to Top

Domain Specific Language

Design Theory

*Back to Top

Design Practises

  • No Grammar to Rule Them All: A Survey of JSON-style DSLs for Visualization - IEEE Transactions on Visualization and Computer Graphics, 2022. [All Versions]. A survey on the design and implementation of 57 JSON-style DSLs for a variety of visualization and visual interaction tasks, suggesting that no one DSL will be able to capture all of them without compromising essential parts of its domain design.

  • Quantifying usability of domain-specific languages: An empirical study on software maintenance - Journal of Systems and Software, 2015. [All Versions]. A study to compare the usability of textual DSLs under the perspective of software maintenance, suggesting that the proposed metrics were useful: (1) to early identify DSL usability limitations, (2) to reveal specific DSL features favoring maintenance tasks, and (3) to successfully analyze eight critical DSL usability dimensions.

  • Communicating Natural Programs to Humans and Machines - NeurIPS'22, 2022. [All Versions]. While humans readily generate and interpret instructions in a general language, computer systems are shackled to a narrow domain-specific language that they can precisely execute. This makes building intelligent systems that can generalize to novel situations such as ARC difficult. Human-generated instructions are referred as `natural programs'. While they resemble computer programs, they are distinct in two ways: First, they contain a wide range of primitives; Second, they frequently leverage communicative strategies beyond directly executable codes.

*Back to Top

Domain Specified Applications

*Back to Top

DSL Program Synthesis

  • pix2code: Generating Code from a Graphical User Interface Screenshot - ACM SIGCHI Symposium on Engineering Interactive Computing Systems, 2018. [All Versions]. [Code]. [Website]. This paper shows that deep learning methods can be leveraged to train a model end-to-end to automatically reverse engineer user interfaces and generate code from a single input image with over 77% of accuracy for three different platforms (i.e. iOS, Android and web-based technologies).

  • Learning to Infer Graphics Programs from Hand-Drawn Images - NeurIPS'18, 2018. [All Versions]. The method learns a model that uses program synthesis techniques to recover a graphics program from drawing primitives. These programs have constructs like variable bindings, iterative loops, or simple kinds of conditionals. With a graphics program in hand, we can correct errors made by the deep network and extrapolate drawings.

*Back to Top

Problem Solving

Human-Level Problem Solving

*Back to Top

Planning

*Back to Top

Intrinsic Motivation

*Back to Top

Reinforcement Learning

*Back to Top

Inverse Reinforcement Learning

*Back to Top

System 1 & System 2

Dual-Coding Theory

*Back to Top

Neural-Symbolic AI

*Back to Top

Explainability

Trustworthy AI

*Back to Top

Strong Machine Learning

*Back to Top

Explainable Deep Learning

*Back to Top

Embodied Intelligence

*Back to Top

Evolutionary Intelligence

*Back to Top

Methodologies for Experiments

Quantitative Analysis

*Back to Top

Scaling Up Behavioral Studies

*Back to Top

Decision Making

*Back to Top

Question Answering

*Back to Top

Human-Machine Comparison

*Back to Top

Association Test

*Back to Top

Virtual Reality

*Back to Top

Meta-Level Considerations

Meta Learning

*Back to Top

Marr's Levels of Analysis

*Back to Top

Gestalt

*Back to Top

The Aha! Moment

*Back to Top

Rationality

*Back to Top

Cognitive Architecture

*Back to Top

Science Logology

Philosophy of Science

*Back to Top

Science of Science

*Back to Top

Literature Mining

*Back to Top

Literature Visualization

*Back to Top

Scientific Writing

*Back to Top

Science Education

*Back to Top

Democratization of Science

*Back to Top

Theory of Mind

  • Theory of Mind - Wikipedia. Wikipedia on Theory of Mind (ToM), a cognitive capability that estimating others' goal, belief, and desire.

*Back to Top

Analogy

*Back to Top

Causality

*Back to Top

Commonsense

Intuitive Physics

*Back to Top

AI Commonsense Reasoning

*Back to Top

Commonsense Knowledgebase

*Back to Top

Inductive Logic & Program Synthesis

*Back to Top

Knowledge Representation

*Back to Top

Cognitive Development

*Back to Top

Learning in the Open World

*Back to Top

Learning with Cognitive Plausibility

*Back to Top

Institute & Researcher

MIT

*Back to Top

Stanford

*Back to Top

Princeton

*Back to Top

Harvard

*Back to Top

UCLA

*Back to Top

UC Berkeley

*Back to Top

BNU

*Back to Top

PKU

*Back to Top

UCSD

*Back to Top

NYU

*Back to Top

JHU

*Back to Top

SIT

*Back to Top

People & Book

Ulf Grenander

Applied mathematician, the founder of General Pattern Theory.

*Back to Top

David Marr

Computational Cognitive Neuroscientist, the establisher of the Levels of Analysis.

*Back to Top

Michael Tomasello

Cognitive scientist, set up the foundations of studying human communications.

*Back to Top

Judea Pearl

Applied mathematician, proposed causal intervention on siamese bayesian networks.

*Back to Top

Susan Carey

Developmental psychologist, proposed object as a core knowledge of human intelligence.

*Back to Top

Daniel Kahneman

Computational cognitive scientist and Economist, set up the foundations for Decision Theory.

*Back to Top

Karl Popper

Scientific philosophor, the founder of scientific verification theories.

*Back to Top

John Hopcroft

Applied Mathematician, theoretical computer scientist.

*Back to Top

About

The initiator of this repo has been struggling to taxonomize related topics, since there are so many perspectives to follow, such as task-oriented, technique-oriented, and metaphysics-oriented. Finally he decided to focus on the perspective of The Sciences of Intelligence---each topic describes a phenomenon of intelligence, or an intelligent behavior---they show the objectives of reverse-engineering human intelligence for computational methods. These topics are never restricted to specific technical methods or tasks, but are trying to organize the nature of intelligence---from both the software perspective and the hardware perspective.

Obviously, this reading list is far from covering the every aspect of AGI and CoCoSci. Since the list is a by-product of the literature reviews when the initiator is working on Abduction and Bayesian modeling, other topics are also collected with biases, more or less. Abduction may be the way humans explain the world with the known, and discover the unknown, requiring much more investigations into its computational basis, cognitive underpinnings, and applications to AI. Please feel free to reach out!

*Back to Top