Maxim ZiatdinovinTowards Data ScienceMaking the “Automated scientist”: Co-navigating the hypothesis and experimental space using…Active learning approach co-navigates theory and experiment via hybrid of reinforcement learning and structured Gaussian Processes13 min read·Dec 14, 2021--1--1
Maxim ZiatdinovinTowards Data ScienceUnknown Knowns, Bayesian Inference, and structured Gaussian ProcessesWhy domain scientists know more ML than they think16 min read·Nov 18, 2021--1--1
Maxim ZiatdinovinTowards Data ScienceDeep Learning Meets Gaussian Process: How Deep Kernel Learning Enables Autonomous MicroscopyMaxim Ziatdinov¹ ² & Sergei V. Kalinin¹10 min read·Nov 2, 2021----
Maxim ZiatdinovinTowards Data ScienceGaussian Process: First Step Towards Active Learning in PhysicsMaxim Ziatdinov¹ ² & Sergei V. Kalinin¹9 min read·Nov 1, 2021----
Maxim ZiatdinovinTowards Data ScienceMastering the shifts with variational autoencodersHow variational autoencoders can be used to analyze one-dimensional signals10 min read·Apr 13, 2021----
Maxim ZiatdinovinTowards Data ScienceEnter the j(r)VAE: divide, (rotate), and order… the cardsIntroduction to joint (rotationally-invariant) VAEs that can perform unsupervised classification and disentangle …12 min read·Mar 11, 2021--1--1
Maxim ZiatdinovinTowards Data ScienceHow we learnt to love the rotationally invariant variational autoencoders (rVAE), and (almost)…Introduction to unsupervised and class-conditioned variational autoencoders (VAEs) with rotational invariance and their application…11 min read·Feb 27, 2021--1--1