Zobrazeno 1 - 10
of 274
pro vyhledávání: '"Utkin, Lev V."'
A method for solving concept-based learning (CBL) problem is proposed. The main idea behind the method is to divide each concept-annotated image into patches, to transform the patches into embeddings by using an autoencoder, and to cluster the embedd
Externí odkaz:
http://arxiv.org/abs/2406.19897
To increase the transparency of modern computer-aided diagnosis (CAD) systems for assessing the malignancy of lung nodules, an interpretable model based on applying the generalized additive models and the concept-based learning is proposed. The model
Externí odkaz:
http://arxiv.org/abs/2405.17483
Autor:
Konstantinov, Andrei V., Utkin, Lev V.
A problem of incorporating the expert rules into machine learning models for extending the concept-based learning is formulated in the paper. It is proposed how to combine logical rules and neural networks predicting the concept probabilities. The fi
Externí odkaz:
http://arxiv.org/abs/2402.14726
A new model for generating survival trajectories and data based on applying an autoencoder of a specific structure is proposed. It solves three tasks. First, it provides predictions in the form of the expected event time and the survival function for
Externí odkaz:
http://arxiv.org/abs/2402.12331
A new approach to the local and global explanation is proposed. It is based on selecting a convex hull constructed for the finite number of points around an explained instance. The convex hull allows us to consider a dual representation of instances
Externí odkaz:
http://arxiv.org/abs/2401.16294
A new method called the Survival Beran-based Neural Importance Model (SurvBeNIM) is proposed. It aims to explain predictions of machine learning survival models, which are in the form of survival or cumulative hazard functions. The main idea behind S
Externí odkaz:
http://arxiv.org/abs/2312.06638
An explanation method called SurvBeX is proposed to interpret predictions of the machine learning survival black-box models. The main idea behind the method is to use the modified Beran estimator as the surrogate explanation model. Coefficients, inco
Externí odkaz:
http://arxiv.org/abs/2308.03730
Autor:
Konstantinov, Andrei V., Utkin, Lev V.
A new computationally simple method of imposing hard convex constraints on the neural network output values is proposed. The key idea behind the method is to map a vector of hidden parameters of the network to a point that is guaranteed to be inside
Externí odkaz:
http://arxiv.org/abs/2307.10459
A new approach called NAF (the Neural Attention Forest) for solving regression and classification tasks under tabular training data is proposed. The main idea behind the proposed NAF model is to introduce the attention mechanism into the random fores
Externí odkaz:
http://arxiv.org/abs/2304.05980
Autor:
Konstantinov, Andrei V., Utkin, Lev V.
A new extremely simple ensemble-based model with the uniformly generated axis-parallel hyper-rectangles as base models (HRBM) is proposed. Two types of HRBMs are studied: closed rectangles and corners. The main idea behind HRBM is to consider and cou
Externí odkaz:
http://arxiv.org/abs/2303.08625