Feed | mysite

All Posts

Dec 9, 2020
1 min

Distributed Hyperparameter Search in Kubeflow/Kubernetes: Keras Tuner vs. Katib

Here is my article on www.medium.com: https://roman-kazinnik.medium.com/distributed-hyperparameter-search-in-kubeflow-kubernetes-keras-t...

1 view0 comments

From Data Pipeline to Machine Learning Architecture in 3 simple pictures

Roman Kazinnik

Dec 9, 2020
1 min

From Data Pipeline to Machine Learning Architecture in 3 simple pictures

Here is my article on medium.com: https://roman-kazinnik.medium.com/from-data-pipeline-to-machine-learning-architecture-in-3-simple-pictu...

2 views0 comments

An Ultimate Guide to Migrating Your Machine Learning to Kubeflow: Excelling in Production in 4 steps

Roman Kazinnik

Jul 17, 2020
1 min

An Ultimate Guide to Migrating Your Machine Learning to Kubeflow: Excelling in Production in 4 steps

My full article in medium.com: https://roman-kazinnik.medium.com/an-ultimate-guide-to-migrating-your-machine-learning-to-kubeflow-4-step...

120 views0 comments

Machine Learning as a Flow: Kubeflow vs. Metaflow

Roman Kazinnik

Feb 24, 2020
1 min

Machine Learning as a Flow: Kubeflow vs. Metaflow

My full article in medium.com: https://roman-kazinnik.medium.com/machine-learning-as-a-flow-kubeflow-vs-metaflow-75f65bd251ec

374 views0 comments

Machine Learning Distributed: Ring-Reduce vs. All-Reduce

Roman Kazinnik

Jan 3, 2020
1 min

Machine Learning Distributed: Ring-Reduce vs. All-Reduce

My full article in medium.com: https://roman-kazinnik.medium.com/machine-learning-distributed-ring-reduce-vs-all-reduce-cb8e97ade42e

120 views0 comments

Roman Kazinnik

Aug 23, 2019
1 min

Convolutional Neural Networks for NLP

The goal of this post is to compare NLP approaches for encoding words: (1) bag of words (2) tfidf (3) google GloVe emeddings Training set...

25 views0 comments

Automate Machine Learning as a Flow: Kubeflow

Roman Kazinnik

Jun 26, 2019
2 min

Automate Machine Learning as a Flow: Kubeflow

I will explain the most recent trends in Machine Learning Automation as a Flow. Examples of ML Flow include Kubeflow by Google, MLFlow, M...

577 views0 comments

Beyond Supervised ML: learning latent distributions

Roman Kazinnik

Feb 17, 2019
2 min

Beyond Supervised ML: learning latent distributions

Supervised ML is a powerful tool, however there is a range of problems where its utilization can't be justified. Such problems include re...

5 views0 comments

Convolutional Neural Networks: recipe to find optimal architecture and avoid redundancy

Roman Kazinnik

Jun 26, 2018
4 min

Convolutional Neural Networks: recipe to find optimal architecture and avoid redundancy

https://github.com/romanonly/romankazinnik_blog/tree/master/CVision/CNN Convolutional Neural Networks (CNN) power in automatically creati...

7 views0 comments

Beyond DAG: Introducing Cyclic Graphs in Neural Networks

Roman Kazinnik

Apr 11, 2018
2 min

Beyond DAG: Introducing Cyclic Graphs in Neural Networks

Deep Learning is driven by the possibility of computing at-scale gradient of the minimization problem for Directed Acyclic Graphs (DAG). ...

219 views0 comments

Approximation theory, AI, and how they actually go together (talk at UNCC)

Roman Kazinnik

Jan 14, 2018
1 min

Approximation theory, AI, and how they actually go together (talk at UNCC)

Here is a video of my talk at the University of North Carolina at Charlotte (01.12.2018). I show how at the beginning of AI, Deep Learni...

84 views0 comments

Beyond Supervised ML: which features are really important? Trial reveals surprising patterns

Roman Kazinnik

Jan 12, 2018
7 min

Beyond Supervised ML: which features are really important? Trial reveals surprising patterns

Trial and error reveal surprising patterns of success—and failure—using different BL and Supervised ML models. When we consider ML (Machi...

39 views0 comments

An Insight into Data Quality: More Data Equals More Work, But Not Necessarily a Better Model

Roman Kazinnik

Jan 8, 2018
4 min

An Insight into Data Quality: More Data Equals More Work, But Not Necessarily a Better Model

In the field of data quality and predictive modeling, which modeling metrics are best at “telling the truth,” so to speak? How did I come...

41 views0 comments

{"items":["5fd084be6dd4120018d8f8f5","5fd083bc04dcd70017a3797d","5f11deefa9a25e001751b805","5e533556778e3e0017a0be6c","5e0fb8ba580d850017978a28","5d606af563123700160706e3","5d139292c313330016864dc8","5c68dadac4799c001c3bdbc8","5b30363dbb6cb9036373e717","5a642643cda1f60b69f02589","5a5b831fae35e208445b0fad","5a580fe52b5ad3025860864c","5a52f9af18447409e1c2a4c8"],"styles":{"galleryType":"Columns","groupSize":1,"showArrows":true,"cubeImages":true,"cubeType":"min","cubeRatio":2.2857142857142856,"isVertical":true,"gallerySize":30,"collageAmount":0,"collageDensity":0,"groupTypes":"1","oneRow":false,"imageMargin":32,"galleryMargin":0,"scatter":0,"rotatingScatter":"","chooseBestGroup":true,"smartCrop":false,"hasThumbnails":false,"enableScroll":true,"isGrid":true,"isSlider":false,"isColumns":false,"isSlideshow":false,"cropOnlyFill":false,"fixedColumns":0,"enableInfiniteScroll":true,"isRTL":false,"minItemSize":50,"rotatingGroupTypes":"","rotatingCropRatios":"","columnWidths":"","gallerySliderImageRatio":1.7777777777777777,"numberOfImagesPerRow":3,"numberOfImagesPerCol":1,"groupsPerStrip":0,"borderRadius":0,"boxShadow":0,"gridStyle":0,"mobilePanorama":false,"placeGroupsLtr":false,"viewMode":"preview","thumbnailSpacings":4,"galleryThumbnailsAlignment":"bottom","isMasonry":false,"isAutoSlideshow":false,"slideshowLoop":false,"autoSlideshowInterval":4,"bottomInfoHeight":0,"titlePlacement":"SHOW_BELOW","galleryTextAlign":"center","scrollSnap":false,"itemClick":"nothing","fullscreen":true,"videoPlay":"hover","scrollAnimation":"NO_EFFECT","slideAnimation":"SCROLL","scrollDirection":0,"scrollDuration":400,"overlayAnimation":"FADE_IN","arrowsPosition":0,"arrowsSize":23,"watermarkOpacity":40,"watermarkSize":40,"useWatermark":true,"watermarkDock":{"top":"auto","left":"auto","right":0,"bottom":0,"transform":"translate3d(0,0,0)"},"loadMoreAmount":"all","defaultShowInfoExpand":1,"allowLinkExpand":true,"expandInfoPosition":0,"allowFullscreenExpand":true,"fullscreenLoop":false,"galleryAlignExpand":"left","addToCartBorderWidth":1,"addToCartButtonText":"","slideshowInfoSize":200,"playButtonForAutoSlideShow":false,"allowSlideshowCounter":false,"hoveringBehaviour":"NEVER_SHOW","thumbnailSize":120,"magicLayoutSeed":1,"imageHoverAnimation":"NO_EFFECT","imagePlacementAnimation":"NO_EFFECT","calculateTextBoxWidthMode":"PERCENT","textBoxHeight":310,"textBoxWidth":200,"textBoxWidthPercent":50,"textImageSpace":10,"textBoxBorderRadius":0,"textBoxBorderWidth":0,"loadMoreButtonText":"","loadMoreButtonBorderWidth":1,"loadMoreButtonBorderRadius":0,"imageInfoType":"ATTACHED_BACKGROUND","itemBorderWidth":1,"itemBorderRadius":0,"itemEnableShadow":false,"itemShadowBlur":20,"itemShadowDirection":135,"itemShadowSize":10,"imageLoadingMode":"BLUR","expandAnimation":"NO_EFFECT","imageQuality":90,"usmToggle":false,"usm_a":0,"usm_r":0,"usm_t":0,"videoSound":false,"videoSpeed":"1","videoLoop":true,"jsonStyleParams":"","gallerySizeType":"px","gallerySizePx":940,"allowTitle":true,"allowContextMenu":true,"textsHorizontalPadding":-30,"itemBorderColor":{"value":"#CCCACA"},"showVideoPlayButton":true,"galleryLayout":2,"calculateTextBoxHeightMode":"MANUAL","textsVerticalPadding":-15,"targetItemSize":940,"selectedLayout":"2|bottom|1|min|true|0|true","layoutsVersion":2,"selectedLayoutV2":2,"isSlideshowFont":true,"externalInfoHeight":310,"externalInfoWidth":0},"container":{"width":940,"galleryWidth":972,"galleryHeight":0,"scrollBase":0,"height":null}}

ML, ML Infra, Math, and in Between.

sign up for my blog and newsletter

Distributed Hyperparameter Search in Kubeflow/Kubernetes: Keras Tuner vs. Katib

From Data Pipeline to Machine Learning Architecture in 3 simple pictures

An Ultimate Guide to Migrating Your Machine Learning to Kubeflow: Excelling in Production in 4 steps

Machine Learning as a Flow: Kubeflow vs. Metaflow

Machine Learning Distributed: Ring-Reduce vs. All-Reduce

Convolutional Neural Networks for NLP

Automate Machine Learning as a Flow: Kubeflow

Beyond Supervised ML: learning latent distributions

Convolutional Neural Networks: recipe to find optimal architecture and avoid redundancy

Beyond DAG: Introducing Cyclic Graphs in Neural Networks

Approximation theory, AI, and how they actually go together (talk at UNCC)

Beyond Supervised ML: which features are really important? Trial reveals surprising patterns

An Insight into Data Quality: More Data Equals More Work, But Not Necessarily a Better Model