Arthur Franz

Odessa Competence Center for Artificial intelligence and Machine learning (OCCAM) · www.occam.com.ua

The inductive programming system WILLIAM is applied to machine learning tasks, in particular, centralization, outlier detection, linear regression, linear classification and decision tree classification. These examples appear as a special case of WILLIAM’s general operation of trying to compress data without any special tuning.

The ability to find short representations, i.e. to compress data, is crucial for many intelligent systems. We present a theory of incremental compression showing that arbitrary data strings, that can be described by a set of features, can be compressed by searching for those features incrementally, which results in a partition of the information co...

The ability to find short representations, i.e. to compress data, is crucial for many intelligent systems. We present a theory of incremental compression showing that arbitrary data strings, that can be described by a set of features, can be compressed by searching for those features incrementally, which results in a partition of the information co...

We present WILLIAM – an inductive programming system based on the theory of incremental compression. It builds representations by incrementally stacking autoencoders made up of trees of general Python functions, thereby stepwise compressing data. It is able to solve a diverse set of tasks including the compression and prediction of simple sequences...

We introduce WILLIAM -- a new system for data compression that is based on a formal mathematical theory of incremental compression. The theory promises to find short descriptions in an incremental and efficient way while still being applicable to a wide range of data. We have used abstract syntax trees of selected Python operators in order to defin...

This book constitutes the proceedings of the 11th International Conference on Artificial General Intelligence, AGI 2018, held in Prague, Czech Republic, in August 2018. The 19 regular papers and 10 poster papers presented in this book were carefully reviewed and selected from 52 submissions. The conference encourage interdisciplinary research base...

Since compressing data incrementally by a non-branching hierarchy has resulted in substantial efficiency gains for performing induction in previous work, we now explore branching hierarchical compression as a means for solving induction problems for generally intelligent systems. Even though assuming the compositionality of data generation and the...

Since compressing data incrementally by a non-branching hierarchy has resulted in substantial efficiency gains for performing induction in previous work, we now explore branching hierarchical compression as a means for solving induction problems for generally intelligent systems. Even though assuming the compositionality of data generation and the...

The ability to induce short descriptions of, i.e. compressing, a wide class of data is essential for any system exhibiting general intelligence. In all generality, it is proven that incremental compression – extracting features of data strings and continuing to compress the residual data variance – leads to a time complexity superior to universal s...

Since universal induction is a central topic in artificial general intelligence (AGI), it is argued that compressing all sequences up to a complexity threshold should be the main thrust of AGI research. A measure for partial progress in AGI is suggested along these lines. By exhaustively executing all two and three state Turing machines a benchmark...

This paper presents a tentative outline for the construction of an artificial, generally intelligent system (AGI). It is argued that building a general data compression algorithm solving all problems up to a complexity threshold should be the main thrust of research. A measure for partial progress in AGI is suggested. Although the details are far f...

The perception of the unity of objects, their permanence when out of sight, and the ability to perceive continuous object trajectories even during occlusion belong to the first and most important capacities that infants have to acquire. Despite much research a unified model of the development of these abilities is still missing. Here we make an att...

Developmental researchers investigate many pieces of infantspsila physical knowledge, e.g. the perception of causality, occlusion or object permanence, but a theoretical framework that would unify all these pieces, account for the most basic phenomena and make testable predictions has not been provided yet. Here we make an attempt to unify and expl...

The role of behavior for the acquisition of sensory representations has been underestimated in the past. We study this question for the task of learning vergence eye movements allowing proper fixation of objects. We model the development of this skill with an artificial neural network based on reinforcement learning. A biologically plausible reward...