13 citations · 26 across the 12 of their papers we have counts for
12 papers
Genetic algorithms with DNN-based trainable crossover as an example of partial specialization of general search
Alexey Potapov, Sergey Rodionov
Universal induction relies on some general search procedure that is doomed to be inefficient. One possibility to achieve both generality and efficiency is to specialize this proced…
Improving Deep Models of Person Re-identification for Cross-Dataset Usage
Sergey Rodionov, Alexey Potapov, Hugo Latapie +2
Person re-identification (Re-ID) is the task of matching humans across cameras with non-overlapping views that has important applications in visual surveillance. Like other compute…
Metric Embedding Autoencoders for Unsupervised Cross-Dataset Transfer Learning
Alexey Potapov, Sergey Rodionov, Hugo Latapie +1
Cross-dataset transfer learning is an important problem in person re-identification (Re-ID). Unfortunately, not too many deep transfer Re-ID models exist for realistic settings of…
HyperNets and their application to learning spatial transformations
Alexey Potapov, Oleg Shcherbakov, Innokentii Zhdanov +2
In this paper we propose a conceptual framework for higher-order artificial neural networks. The idea of higher-order networks arises naturally when a model is required to learn so…
Vision System for AGI: Problems and Directions
Alexey Potapov, Sergey Rodionov, Maxim Peterson +3
What frameworks and architectures are necessary to create a vision system for AGI? In this paper, we propose a formal model that states the task of perception within AGI. We show t…
Local ensemble transform Kalman filter, a fast non-stationary control law for adaptive optics on ELTs: theoretical aspects and first simulation results
Morgan Gray, Cyril Petit, Sergey Rodionov +4
We propose a new algorithm for an adaptive optics system control law, based on the Linear Quadratic Gaussian approach and a Kalman Filter adaptation with localizations. It allows t…
Local Ensemble Transform Kalman Filter: a non-stationary control law for complex adaptive optics systems on ELTs
Morgan Gray, Cyril Petit, Sergey Rodionov +3
We propose a new algorithm for an adaptive optics system control law which allows to reduce the computational burden in the case of an Extremely Large Telescope (ELT) and to deal w…
Universal Empathy and Ethical Bias for Artificial General Intelligence
Alexey Potapov, Sergey Rodionov
Rational agents are usually built to maximize rewards. However, AGI agents can find undesirable ways of maximizing any prior reward function. Therefore value learning is crucial fo…
Direct Uncertainty Estimation in Reinforcement Learning
Sergey Rodionov, Alexey Potapov, Yurii Vinogradov
Optimal probabilistic approach in reinforcement learning is computationally infeasible. Its simplification consisting in neglecting difference between true environment and its mode…
Extending Universal Intelligence Models with Formal Notion of Representation
Alexey Potapov, Sergey Rodionov
Solomonoff induction is known to be universal, but incomputable. Its approximations, namely, the Minimum Description (or Message) Length (MDL) principles, are adopted in practice i…
Universal Induction with Varying Sets of Combinators
Alexey Potapov, Sergey Rodionov
Universal induction is a crucial issue in AGI. Its practical applicability can be achieved by the choice of the reference machine or representation of algorithms agreed with the en…
Cognitive Bias for Universal Algorithmic Intelligence
Alexey Potapov, Sergey Rodionov, Andrew Myasnikov +1
Existing theoretical universal algorithmic intelligence models are not practically realizable. More pragmatic approach to artificial general intelligence is based on cognitive arch…