Intelligent systems's repositories
hippotrainer
[BMM 24-25] HippoTrainer: Gradient-Based Hyperparameter Optimization
CreationOfIntelligentSystems_Simultaneous_fMRI-EEG
The problem of decoding simultaneously collected EEG-fMRI data is under investigation.
m1p-MSU-FALL2024
Course on M1P for MSU
.github
Special profile rep
2025-Project-182
[m1p 2025] Convergence of the loss function surface in transformer neural network architectures
2025-Project-183
[m1p 2025] Neural Networks Loss Landscape Convergence in Different Low-Dimensional Spaces
2025-Project-188
First scientific paper – Comparison of various models for flood prediction.
bmm-multitask-learning
Multi-task learning is a machine learning paradigm which involves optimization model parameters for multiple diverse tasks.
DFDistill
Data-free distillation package based on PyTorch
Kalman-filter-and-his-friends
Kalman filter and extensions
Khafizov-BS-Thesis
Адаптивное сжатие в распределенной оптимизации
n_ode
Neural ODE classification
text-tree-distance
Repository for MIPT All-Russian Scientific Conference work "A method for text tree similarity estimation using tree edit distance and language models"
tssa_method
Исследуется тензорный метод декомпозиции и предсказания временных рядов tSSA
Vector-space-of-generative-models
Задан набор генеративных моделей, описывающий разные выборки/генеральные совокупности данных. Требуется предложить метод векторного представления этих моделей, который будет представлять их статистические свойства.