Towards Heuristic Algorithmic Memory

Özkural, Eray

doi:10.1007/978-3-642-22887-2_47

Cited by 6 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 1984, Solomonoff observed that KUSP machines are especially suitable for incremental learning [11]. In our work [25] we found that, the incremental learning approach was indeed useful (as in the preceding OOPS algorithm [26]). Here is how we interpreted incremental learning.…”

Section: Incremental Machine Learningsupporting

confidence: 66%

“…During the experimental tests of our Stochastic Context Free Grammar based search and update algorithms [25], we have observed that in practice we can realize fast updates, and we can still achieve actual code re-use and tremendous speed-up. Using only 0.5 teraflop/sec of computing speed and a reference machine choice of R5RS Scheme [27], we solved 6 simple deterministic operator induction problems in 245.1 seconds.…”

Section: Incremental Machine Learningmentioning

confidence: 99%

See 1 more Smart Citation

Diverse Consequences of Algorithmic Probability

Özkural

2013

Algorithmic Probability and Friends. Bayesian Prediction and Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

Abstract. We reminisce and discuss applications of algorithmic probability to a wide range of problems in artificial intelligence, philosophy and technological society. We propose that Solomonoff has effectively axiomatized the field of artificial intelligence, therefore establishing it as a rigorous scientific discipline. We also relate to our own work in incremental machine learning and philosophy of complexity.

show abstract

Section: Incremental Machine Learningsupporting

confidence: 66%

Section: Incremental Machine Learningmentioning

confidence: 99%

Diverse Consequences of Algorithmic Probability

Özkural

2013

Algorithmic Probability and Friends. Bayesian Prediction and Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

show abstract

“…• Teramachine [32]: a universal inductive inference engine that partially solves the memory and parallelism problems.…”

Section: Artificial General Intelligencementioning

confidence: 99%

“…An extremely advanced formulation of the optimizing/goal-following agents is possible due to Solomonoff's general-purpose AI system Alpha, stage 2 [39] which can solve time-limited free-form optimization problems. Alpha is of particular interest to us because it is the culmination of our research program, as teramachine was conceived as a candidate for Alpha, stage 1 [32]. Shortly, merely collecting as much information as possible is not enough.…”

Section: Advanced Formulation Of Ai Probementioning

confidence: 99%

Articial Intelligence and Brain Simulation Probes for Interstellar Expeditions

Özkural¹

2018

Preprint

Self Cite

View full text Add to dashboard Cite

We introduce a mission design for an interstellar expedition to nearby earth-like exoplanets, which our analysis determined to be Tau Ceti and Gliese 667C, at the time of analysis in 2013. We review the research problems in propulsion and AGI that must be addressed to launch an AI guided interstellar probe within 100 years. We propose a new semi-autonomous agent approach for intelligent control of the spacecraft. We introduce the concept of a semi-autonomous agent as having built-in safety guarantees that constrain operation. An autonomous agent case study is presented formulating the objective, constraints, AGI implementation of the agent based on Solomono's Alpha architecture, and adding specicity. We discuss the training required to reach human-level and trans-sapient levels of intelligence which corresponds to an entire crew of AI experts specialized in elds such as astrophysics, astromechanics, astrobiology, quantum physics, computer science, molecular biology, and so forth. We project the feasibility of the human-level AI technology based on empirical ndings in neuroscience, and  nd that it should be feasible by 2030. We analyze Solomono's innity point hypothesis in light of Koomey's law about energy eciency of computing and nd that the trends in 2013 indicated an early singularity by 2035, which implies that we might encounter physical bottlenecks which will decelerate computing technology improvements signicantly. We recommend thus year 2040 for launching the probe by which date other required technologies will have been developed. We discuss the scenario of a virtual crew made of brain simulations, which is a bio-information based AI approach. We detail the subsystems of command and control, communication, scientic instrumentation, power, propulsion, navigation, and shielding. We propose a variation of ICAN-II/AIMStar propulsion which uses a positron source instead of anti-protons to initiate micro-fusion reactions. We combine the positron initiated fusion pulse propulsion scheme with a miniaturized version of the Daedelus fusion thruster obtaining high performance. We derive two mission proles one for fusion pulse propulsion, and the yet hypothetical Q-Thruster. Fusion thruster requires 132.2 years for Tau Ceti, and 233.2 years for Gliese 667C, while Q-Thruster takes only 42.3 years for Tau Ceti, and 62.5 years for Gliese 667C. We also discuss extended roles for intelligent interstellar probes such as self-reproduction via nanotechnology, refueling, construction, robotic bodies, and transmission of brain simulations.

show abstract

An Inferential Approach to Mining Surprising Patterns in Hypergraphs

Geisweiller¹,

Goertzel²

2019

Artificial General Intelligence

View full text Add to dashboard Cite

Towards Heuristic Algorithmic Memory

Cited by 6 publications

References 9 publications

Diverse Consequences of Algorithmic Probability

Diverse Consequences of Algorithmic Probability

Articial Intelligence and Brain Simulation Probes for Interstellar Expeditions

An Inferential Approach to Mining Surprising Patterns in Hypergraphs

Contact Info

Product

Resources

About