#### Filter Results:

#### Publication Year

2004

2016

#### Co-author

#### Key Phrase

#### Publication Venue

Learn More

It is known that benign looking AI objectives may result in powerful AI drives that may pose a risk to the human society. We examine the alternative scenario of what happens when universal goals that are not human-centric are used for designing AI agents. We follow a design approach that tries to exclude malevolent motivations from AI's, however, we see… (More)

—We introduce a transaction database distribution scheme that divides the frequent item set mining task in a top-down fashion. Our method operates on a graph where vertices correspond to frequent items and edges correspond to frequent item sets of size two. We show that partitioning this graph by a vertex separator is sufficient to decide a distribution of… (More)

Frequency mining problem comprises the core of several data mining algorithms. Among frequent pattern discovery algorithms, FP-GROWTH employs a unique search strategy using compact structures resulting in a high performance algorithm that requires only two database passes. We introduce an enhanced version of this algorithm called FP-GROWTH-TINY which can… (More)

- Eray Özkural
- AGI
- 2011

- Eray Özkural
- AGI
- 2012

We frame the question of what kind of subjective experience a brain simulation would have in contrast to a biological brain. We discuss the brain prosthe-sis thought experiment. Then, we identify finer questions relating to the original inquiry, and set out to answer them moving forward from both a general physi-calist perspective, and pan-experientialism.… (More)

- Eray Özkural
- AGI
- 2016

- Eray Özkural
- AGI
- 2015

We argue that Solomonoff induction is universal and complete in the physical sense via several strong physical arguments. We argue that Solomonoff induction is fully applicable to quantum mechanics. We show how to choose an objective reference machine for universal induction by defining a physical message complexity for the presently considered ultimate… (More)

We investigate physical measures and limits of intelligence that are objective and useful. We propose a universal measure of operator induction fitness, and show how it can be used in a reinforcement learning model, and a self-preserving agent model based on the free energy principle. We extend logical depth and conceptual jump size measures to stochastic… (More)

- Eray Özkural
- AGI
- 2014

We generalize Solomonoff's stochastic context-free grammar induction method to context-sensitive grammars, and apply it to transfer learning problem by means of an efficient update algorithm. The stochastic grammar serves as a guiding program distribution which improves future probabilistic induction approximations by learning about the training sequence of… (More)