Sergey Rodionov

Making Universal Induction Efficient by Specialization

Efficient pragmatic methods in artificial intelligence can be treated as results of specialization of models of universal intelligence with respect to a certain task or class of environments. Thus, specialization can help to create efficient AGI preserving its universality. This idea is promising, but has not yet been applied to concrete models. Here, we considered the task of mass induction, which general solution can be based on Kolmogorov complexity parameterized by reference machine. Futamura-Turchin projections of this solution were derived and implemented in combinatory logic. Experiments with search for common regularities in strings show that efficiency of universal induction can be considerably increased for mass induction using proposed approach.

Universal empathy and ethical bias for artificial general intelligence

Rational agents are usually built to maximise rewards. However, artificial general intelligence (AGI) agents can find undesirable ways of maximising any prior reward function. Therefore, value learning is crucial for safe AGI. We assume that generalised states of the world are valuable – not rewards themselves, and propose an extension of AIXI, in which rewards are used only to bootstrap hierarchical value learning. The modified AIXI agent is considered in the multi-agent environment, where other agents can be either humans or other ‘mature’ agents, the values of which should be revealed and adopted by the ‘infant’ AGI agent. A general framework for designing such empathic agent with ethical bias is proposed as an extension of the universal intelligence model as well. Moreover, we perform experiments in the simple Markov environment, which demonstrate feasibility of our approach to value learning in safe AGI.

Optimization Framework with Minimum Description Length Principle for Probabilistic Programming

Application of the Minimum Description Length principle to optimization queries in probabilistic programming was investigated on the example of the C++ probabilistic programming library under development. It was shown that incorporation of this criterion is essential for optimization queries to behave similarly to more common queries performing sampling in accordance with posterior distributions and automatically implementing the Bayesian Occams razor. Experimental validation was conducted on the task of blood cell detection on microscopic images. Detection appeared to be possible using genetic programming query, and automatic penalization of candidate solution complexity allowed to choose the number of cells correctly avoiding overfitting.

Universal induction with varying sets of combinators

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 environment. This machine should be updatable for solving subsequent tasks more efficiently. We study this problem on an example of combinatory logic as the very simple Turing-complete reference machine, which enables modifying program representations by introducing different sets of primitive combinators. Genetic programming system is used to search for combinator expressions, which are easily decomposed into sub-expressions being recombined in crossover. Our experiments show that low-complexity induction or prediction tasks can be solved by the developed system (much more efficiently than using brute force); useful combinators can be revealed and included into the representation simplifying more difficult tasks. However, optimal sets of combinators depend on the specific task, so the reference machine should be adaptively chosen in coordination with the search engine.

Real-Time GA-Based Probabilistic Programming in Application to Robot Control

Possibility to solve the problem of planning and plan recovery for robots using probabilistic programming with optimization queries, which is being developed as a framework for AGI and cognitive architectures, is considered. Planning can be done directly by introducing a generative model for plans and optimizing an objective function calculated via plan simulation. Plan recovery is achieved almost without modifying optimization queries. These queries are simply executed in parallel with plan execution by a robot meaning that they continuously optimize dynamically varying objective functions tracking their optima. Experiments with the NAO robot showed that replanning can be naturally done within this approach without developing special plan recovery methods.

Extending universal intelligence models with formal notion of representation

Solomonoff induction is known to be universal, but incomputable. Its approximations, namely, the Minimum Description (or Message) Length (MDL) principles, are adopted in practice in the efficient, but non-universal form. Recent attempts to bridge this gap leaded to development of the Representational MDL principle that originates from formal decomposition of the task of induction. In this paper, possible extension of the RMDL principle in the context of universal intelligence agents is considered, for which introduction of representations is shown to be an unavoidable meta-heuristic and a step toward efficient general intelligence. Hierarchical representations and model optimization with the use of information-theoretic interpretation of the adaptive resonance are also discussed.

Local ensemble transform Kalman filter, a fast non-stationary control law for adaptive optics on ELTs: theoretical aspects and first simulation results

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 to handle non-stationary behaviors, to obtain performance close to the optimality defined with the residual phase variance minimization criterion, and to reduce the computational burden with an intrinsically parallel implementation on the Extremely Large Telescopes (ELTs).

HyperNets and Their Application to Learning Spatial Transformations

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 some group of transformations, every element of which is well-approximated by a traditional feedforward network. Thus the group as a whole can be represented as a hyper network. One of typical examples of such groups is spatial transformations. We show that the proposed framework, which we call HyperNets, is able to deal with at least two basic spatial transformations of images: rotation and affine transformation. We show that HyperNets are able not only to generalize rotation and affine transformation, but also to compensate the rotation of images bringing them into canonical forms.

Improving Deep Models of Person Re-identification for Cross-Dataset Usage

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 computer vision tasks, this task has gained much with the utilization of deep learning methods. However, existing solutions based on deep learning are usually trained and tested on samples taken from same datasets, while in practice one need to deploy Re-ID systems for new sets of cameras for which labeled data is unavailable. Here, we mitigate this problem for one state-of-the-art model, namely, metric embedding trained with the use of the triplet loss function, although our results can be extended to other models. The contribution of our work consists in developing a method of training the model on multiple datasets, and a method for its online practically unsupervised fine-tuning. These methods yield up to 19.1% improvement in Rank-1 score in the cross-dataset evaluation.

Vision System for AGI: Problems and Directions

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 the role of discriminative and generative models in achieving efficient and general solution of this task, thus specifying the task in more detail. We discuss some existing generative and discriminative models and demonstrate their insufficiency for our purposes. Finally, we discuss some architectural dilemmas and open questions.