Russian Federation

A novel computational model (CoDD) utilizing combinatory logic to create higher-order decision trees is presented. A theoretical analysis of general intelligence in terms of the formal theory of pattern recognition and pattern formation is outlined, and shown to take especially natural form in the case where patterns are expressed in CoDD language. Relationships between logical entropy and algorithmic information, and Shannon entropy and runtime complexity, are shown to be elucidated by this approach. Extension to the quantum computing case is also briefly discussed.

AGI-20

Combinatorial Decision Dags: A Natural Computational Model for General Intelligence

decision tree complexity

combinatory logic

logical entropy

quantum computing

The Institute of Physics and IOP Publishing, in partnership with the Chinese Physical Society (CPS) and the University of Science and Technology of China (USTC) are proud to have brought together the international quantum science community online for this inaugural conference.


Early career and leading researchers from universities, industry and government worldwide came together to share, learn and collaborate on the latest research and emerging areas of high interest across quantum science and technology. The broad themes covered by Quantum 2020 included:

Quantum communication;
Quantum computing and quantum simulation;
Quantum sensing, metrology and imaging;
Quantum information theory, software and algorithms;
Quantum foundations;
Quantum technology in industry.
The four-day event featured talks from world-renowned scientists, interactive poster sessions and two exciting panel discussions on the themes of Quantum Technology in Industry and Quantum Technology Programmes Around the World.


You will need to [register](https://www.iopconferences.org/iop/frontend/reg/tRegisterEmailNew.csp?pageID=978403&eventID=1552&tempPersonID=536224) to obtain a ticket. . If you have already registered you should have been sent an email from Underline (to the email address that you registered with) with the subject line ‘Welcome to Quantum 2020’. This email includes your ticket for the event. 

If you have a ticket and are experiencing problems in accessing the event, please contact us. 

Quantum 2020

The Institute of Physics and IOP Publishing, in partnership with the Chinese Physical Society (CPS) and the University of Science and Technology of China (USTC) are proud to have brought together the international quantum science community online for this inaugural conference.

Early career and leading researchers from universities, industry and government worldwide came together to share, learn and collaborate on the latest research and emerging areas of high interest across quantum science and technology. 

technical paper

The AGI conference series is the only major conference series devoted wholly and specifically to the creation of AI systems possessing general intelligence at the human level and ultimately beyond. By gathering together active researchers in the field, for presentation of results and discussion of ideas, we accelerate our progress toward our common goal.

Underline hosted the two main days of AGI 2020 on Wednesday June 24th and Thursday June 25th. Both days were **live-streamed** and you can read the full program bellow. All presentations are available for a **asynchronous viewing**. All presenters are grouped into panels. You can also hear guest talks by **Ben Goertzel** (SingularityNET), **Valery Tarasov** (Semenov Institute of Chemical Physics), **Tatiana Shavrina** (Sberbank) and **Joscha Bach** (MIT Media Lab). 

The AGI conference series is the only major conference series devoted wholly and specifically to the creation of AI systems possessing general intelligence at the human level and ultimately beyond. By gathering together active researchers in the field, for presentation of results and discussion of ideas, we accelerate our progress toward our common goal.

A recently developed Functional Modeling Framework suggests that all models of cognition can be represented by a minimally reducible set of functions, and proposes to define the criteria for a model of cognition to have the potential for the general problem solving ability commonly recognized as true human intelligence. This human-centric functional modeling approach is intended to enable different models of AGI to be more easily compared so research can reliably converge on a single understanding, enabling the possibility of massively collaborative interdisciplinary projects to research and implement models of consciousness or cognition where difficulty in communicating very different ideas, particularly in the case of new models without a significant following, has prevented such massive collaboration from in practice having proved possible before. This paper summarizes a model of cognition developed within this framework.

A Model of Artificial General Intelligence

Can an AGI create a more intelligent AGI? Under idealized assumptions, for a certain theoretical type of intelligence, our answer is: “Not without outside help”. This is a presentation on the mathematical structure of AGI populations when parent AGIs create child AGIs. We argue that such populations satisfy a certain biological law. Motivated by observations of sexual reproduction in seemingly-asexual species, the Knight-Darwin Law states that it is impossible for one organism to asexually produce another, which asexually produces another, and so on forever: that any sequence of organisms (each one a child of the previous) must contain occasional multi-parent organisms, or must terminate. By proving that a certain measure (arguably an intelligence measure) decreases when an idealized parent AGI single-handedly creates a child AGI, we argue that a similar Law holds for AGIs.

AGI and the Knight-Darwin Law

While several tools exist for training and evaluating narrow machine learning (ML) algorithms, their design generally does not follow a particular or explicit evaluation methodology or theory. Inversely so for more general learners, where many evaluation methodologies and frameworks have been suggested, but few specific tools exist. In this paper we introduce a new framework for broad evaluation of artificial intelligence (AI) learners, and a new tool that builds on this methodology. The platform, called SAGE (Simulator for Autonomy \& Generality Evaluation), works for training and evaluation of a broad range of systems and allows detailed comparison between narrow and general ML and AI. It provides a variety of tuning and task construction options, allowing isolation of single parameters across complexity dimensions. SAGE is aimed at helping AI researchers map out and compare strengths and weaknesses of divergent approaches. Our hope is that it can help deepen understanding of the various tasks we want AI systems to do and the relationship between their composition, complexity, and difficulty for various AI systems, as well as contribute to building a clearer research road map for the field. This paper provides an overview of the framework and presents results of an early use case.

SAGE: Task-Environment Platform for Evaluating a Broad Range of AI Learners

We introduce the open-ended, modular, self-improving Omega AI unification architecture which is a refinement of Solomonoff's Alpha architecture, as considered from first principles. The architecture embodies several crucial principles of general intelligence including diversity of representations, diversity of data types, integrated memory, modularity, and higher-order cognition. We retain the basic design of a fundamental algorithmic substrate called an ``AI kernel'' for problem solving and basic cognitive functions like memory, and a larger, modular architecture that re-uses the kernel in many ways. Omega includes eight representation languages, which are briefly introduced. We review the broad software architecture, higher-order cognition, self-improvement, modular neural architectures, and intelligent agents.

Omega: An Architecture for AI Unification

From Psychonics to Artificial General Intelligence and Hybrid Intelligence

Texts as an unlimited, but indirect trace of human thinking processes are the richest source for AI modelling that we have. How to handle it and where does SuperGLUE come about - let's find out together.

Russian SuperGLUE Creating a Language Understanding Evaluation Benchmark

Panel discussion with authors of papers about 'Cognitive Architectures and Agents' at AGI-20 conference. Held live on Underline, 06/24/2020

Panel Session 1: Cognitive Architectures and Agents

Panel discussion with authors of papers about 'Intelligence measures, AGI Benchmarks and Evaluations' at AGI-20 conference. Held live on Underline, 06/24/2020

Panel Session 2: Intelligence measures, AGI Benchmarks and Evaluations

Panel discussion with authors of papers about 'Learning, Reasoning, and Resource Allocation' at AGI-20 conference. Held live on Underline, 06/24/2020

Combinatorial Decision Dags: A Natural Computational Model for General Intelligence

Downloads

Next from AGI-20

A Model of Artificial General Intelligence

Similar lecture

Exploring hybrid quantum-classical neural networks for particle tracking

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Combinatorial Decision Dags: A Natural Computational Model for General Intelligence

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AGI-20

A Model of Artificial General Intelligence

Similar lecture

Exploring hybrid quantum-classical neural networks for particle tracking

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads