Open in app

Sign In

Write

Sign In

Maxim Ziatdinov
Maxim Ziatdinov

98 Followers

Home

About

Published in

Towards Data Science

·Dec 14, 2021

Making the “Automated scientist”: Co-navigating the hypothesis and experimental space using structured Gaussian Processes

Maxim Ziatdinov¹ ² & Sergei V. Kalinin¹ ¹ Center for Nanophase Materials Sciences and ² Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, United States Experimental scientific research is one of the most fascinating activities known to mankind (at least, in the highly subjective opinion…

Gaussian Process

13 min read

Making the “Automated scientist”: Co-navigating the hypothesis and experimental space using…
Making the “Automated scientist”: Co-navigating the hypothesis and experimental space using…
Gaussian Process

13 min read


Published in

Towards Data Science

·Nov 18, 2021

Unknown Knowns, Bayesian Inference, and structured Gaussian Processes

Why domain scientists know more ML than they think — Maxim Ziatdinov¹ ² & Sergei V. Kalinin¹ ¹ Center for Nanophase Materials Sciences and ² Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, United States About 20 years ago, Donald Rumsfeld, the erstwhile minister of defense, famously said referring to the intelligence situation, “…there are…

Active Learning

16 min read

Unknown Knowns, Bayesian Inference, and structured Gaussian Processes
Unknown Knowns, Bayesian Inference, and structured Gaussian Processes
Active Learning

16 min read


Published in

Towards Data Science

·Nov 2, 2021

Deep Learning Meets Gaussian Process: How Deep Kernel Learning Enables Autonomous Microscopy

Maxim Ziatdinov¹ ² & Sergei V. Kalinin¹ ¹ Center for Nanophase Materials Sciences and ² Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, United States For many scientists and engineers, the road towards their profession started from microscopy. Under a simple optical microscope or a…

Deep Learning

10 min read

Deep Learning Meets Gaussian Process: How Deep Kernel Learning Enables Autonomous Microscopy
Deep Learning Meets Gaussian Process: How Deep Kernel Learning Enables Autonomous Microscopy
Deep Learning

10 min read


Published in

Towards Data Science

·Nov 1, 2021

Gaussian Process: First Step Towards Active Learning in Physics

Maxim Ziatdinov¹ ² & Sergei V. Kalinin¹ ¹ Center for Nanophase Materials Sciences and ² Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, United States Despite the extreme disparity in terms of objects and study methods, some tasks are common across multiple scientific fields. One…

Gaussian Process

9 min read

Gaussian Process: First Step Towards Active Learning in Physics
Gaussian Process: First Step Towards Active Learning in Physics
Gaussian Process

9 min read


Published in

Towards Data Science

·Apr 13, 2021

Mastering the shifts with variational autoencoders

How variational autoencoders can be used to analyze one-dimensional signals — Maxim Ziatdinov¹ ² & Sergei V. Kalinin¹ ¹ Center for Nanophase Materials Sciences and ² Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, United States Data often comes in the form of one-dimensional signals. These can be the time series recording from a sensor or…

Variational Autoencoder

10 min read

Mastering the shifts with variational autoencoders
Mastering the shifts with variational autoencoders
Variational Autoencoder

10 min read


Published in

Towards Data Science

·Mar 11, 2021

Enter the j(r)VAE: divide, (rotate), and order… the cards

Introduction to joint (rotationally-invariant) VAEs that can perform unsupervised classification and disentangle relevant (continuous) factors of variation at the same time. — Maxim Ziatdinov¹ ² & Sergei V. Kalinin¹ ¹ Center for Nanophase Materials Sciences and ² Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, United States What are joint (rotationally-invariant) variational autoencoders, and why would we need them? The short answer to the first question is…

Variational Autoencoder

12 min read

Enter the j(r)VAE: divide, (rotate), and order… the cards
Enter the j(r)VAE: divide, (rotate), and order… the cards
Variational Autoencoder

12 min read


Published in

Towards Data Science

·Feb 27, 2021

How we learnt to love the rotationally invariant variational autoencoders (rVAE), and (almost) stopped doing PCA

Introduction to unsupervised and class-conditioned variational autoencoders (VAEs) with rotational invariance and their application to image analysis — Maxim Ziatdinov¹ ² & Sergei V. Kalinin¹ ¹ Center for Nanophase Materials Sciences and ² Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, United States Scientific research often yields enormous volumes of data. The examples range from fields such as astronomy with its exquisite optical…

Deep Learning

11 min read

How we learnt to love the rotationally invariant variational autoencoders (rVAE), and (almost)…
How we learnt to love the rotationally invariant variational autoencoders (rVAE), and (almost)…
Deep Learning

11 min read

Maxim Ziatdinov

Maxim Ziatdinov

98 Followers

Research Scientist — Experimental Physics, Nanoscience, Machine learning. ❤️ Open Source. https://twitter.com/MaximZiatdinov/

Following
  • Toyota Research Institute

    Toyota Research Institute

  • Carlos E. Perez

    Carlos E. Perez

  • Eric Johnson

    Eric Johnson

  • Pedro Domingos

    Pedro Domingos

  • Chris Mingard

    Chris Mingard

See all (15)

Help

Status

Writers

Blog

Careers

Privacy

Terms

About

Text to speech

Teams