Artem Chernodub

E-mail:

LinkedIn page

https://www.linkedin.com/in/artem-chernodub-556291b1/

In 2007 he got Ms.Sc. from Moscow Institute of Physics and Technology, in 2016 he defended his Ph.D. thesis “Training the Dynamic Neural Networks for Long-term Predictions” in the Institute of Mathematical Machines and Systems NASU. Scientific interests: Artificial Neural Networks, Deep Learning, Natural Language Processing.

Artificial neural networks, deep learning, natural language processing.

Artem Chernodub and Dimitri Nowicki. Orthogonal Permutation Linear Unit Activation Function (OPLU) // 25-th International Conference on Artificial Neural Networks ICANN’2016, (Barcelona, Spain, 6–9 September 2016). Lecture Notes in Computer Science. – Berlin Heidelberg: Springer-Verlag, 2016. – Vol. 9887. – P. 533 – 534.

Artem Chernodub and Dimitri Nowicki. Sampling-based Gradient Regularization for Capturing Long-Term Dependencies in Recurrent Neural Networks // 23rd International Conference on Neural Information Processing ICONIP’2016 (Kyoto, Japan, 16–21 October 2016). Lecture Notes in Computer Science. – Berlin Heidelberg: Springer-Verlag, 2016. – Vol. 9948. – P. 90-97.

Artem Chernodub. Training Dynamic Neural Networks Using the Extended Kalman Filter for Multi-Step-Ahead Predictions // Artificial Neural Networks Methods and Applications in Bio-Neuroinformatics / P. Koprinkova-Hristova, V. Mladenov, N.K. Kasabov (eds.). Springer International Publishing Switzerland, 2015.– Vol. 4. – P. 221 – 244.

A.M. Reznik, D.N. Nowicki, A.N. Chernodub, D.A. Dziuba. Phase-Correlation Method for 3D Visual Navigation using Single Camera // 3rd IEEE International Conference “Actual Problems of Unmanned Aerial Vehicles Develop-ments (APUAVD-2015)”, Kyiv, Ukraine, 2015, p. 186-188.

Artem Chernodub. Training Neural Networks for Classification Using the Extended Kalman Filter: A Comparative study // Optical Memory and Neural Networks. – 2014. – Vol. 23, Issue 2. – P. 96 – 103.

Artem Chernodub. Direct Method for Training Feed-Forward Neural Networks Using Batch Extended Kalman Filter for Multi-Step-Ahead Predictions // Artificial Neural Networks and Machine Learning – ICANN 2013. Lecture Notes in Computer Science, Springer-Verlag, Berlin Heidelberg 2013, Vol. 8131, P. 138 – 145.