41 citations · 41 across the 3 of their papers we have counts for
3 papers
Formation of structural attractors in neuromorphic systems
Yurii Parzhyn, Alexander Schwarzmann, Mykyta Lapin +1
This paper examines the theory of Invariant Structural Learning (ISL), which proposes a non-optimization approach to concept formation. Learning is interpreted as convergence to st…
Few-Shot Learning of a Graph-Based Neural Network Model Without Backpropagation
Mykyta Lapin, Kostiantyn Bokhan, Yurii Parzhyn
We propose a structural-graph approach to classifying contour images in a few-shot regime without using backpropagation. The core idea is to make structure the carrier of explanati…
Accelerating recurrent neural network training using sequence bucketing and multi-GPU data parallelization
Viacheslav Khomenko, Oleg Shyshkov, Olga Radyvonenko +1
An efficient algorithm for recurrent neural network training is presented. The approach increases the training speed for tasks where a length of the input sequence may vary signifi…