Evgenii Dzhivelikian

Moscow Institute of Physics and Technology | MIPT · Department of Control/Management and Applied Mathematics

Learning models online in partially observable stochastic environments can still be challenging for artificial intelligent agents. In this paper, we propose an algorithm for the probabilistic modeling of observation sequences based on the neurophysiological model of the human cortex, which is notoriously fit for this task. We argue that each dendri...

For autonomous AI systems, it is important to process spatiotemporal information to encode and memorize it and extract and reuse abstractions effectively. What is natural for natural intelligence is still a challenge for AI systems. In this paper, we propose a biologically plausible model of spatiotemporal memory with an attractor module and study...

Artificial intelligence systems operating in the sequential decision making paradigm are inevitably required to do effective spatio-temporal processing. The memory models for such systems are often required not just to memorize the observed data stream, but also to encode it so it is possible to separate dissimilar sequences and consolidate similar...

Biologically plausible models of learning may provide a crucial insight for building autonomous intelligent agents capable of performing a wide range of tasks. In this work, we propose a hierarchical model of an agent operating in an unfamiliar environment driven by a reinforcement signal. We use temporal memory to learn sparse distributed represen...

In this paper, we propose a biologically plausible model for learning the decision-making sequence in an external environment with internal motivation. As a computational model, we propose a hierarchical architecture of an intelligent agent acquiring experience based on reinforcement learning. We use the basal ganglia model to aggregate a reward, a...