Jonathan Kernes – Medium

Jonathan Kernes

Jonathan Kernes
in
Towards Data Science

Diffusion Models

What are they, how do they work, and why now?

Dec 13, 2022

Diffusion Models

Dec 13, 2022

Jonathan Kernes
in
Ntropy

The False Promise of General Transaction Categorization and the inadequacy of in-house models

Why the Ntropy customized model approach is the only solution for high performance

May 24, 2022

The False Promise of General Transaction Categorization and the inadequacy of in-house models

May 24, 2022

Jonathan Kernes
in
Ntropy

Customized Transaction Classification

Successes, benchmarking, and how to maximize your performance. Bringing meta-learning to production.

Apr 19, 2022

Customized Transaction Classification

Apr 19, 2022

Jonathan Kernes
in
Ntropy

Quickly finding recurring events in massive sequences

A scalable O(N*K) solution for sequences of size N and max intervals of size K

Feb 20, 2022

Quickly finding recurring events in massive sequences

Feb 20, 2022

Jonathan Kernes
in
Towards Data Science

Master Positional Encoding: Part II

We upgrade to relative position, present a bi-directional relative encoding, and discuss the pros and cons of letting the model learn this…

Feb 25, 2021

Master Positional Encoding: Part II

Feb 25, 2021

Jonathan Kernes
in
Towards Data Science

Master Positional Encoding: Part I

We present a “derivation” of the fixed positional encoding that powers Transformers, helping you get a full intuitive understanding.

Feb 15, 2021

Master Positional Encoding: Part I

Feb 15, 2021

Jonathan Kernes
in
Towards Data Science

Build Your Own Automatic Differentiation Program

For anyone who’s completely lost at how graphs can be used to compute derivatives, or just wants to know how TensorFlow works at a…

Feb 9, 2021

Build Your Own Automatic Differentiation Program

Feb 9, 2021

Jonathan Kernes
in
Towards Data Science

How to Overcome the Large Vocabulary Bottleneck Using an Adaptive Softmax Layer

A detailed guide to how a simple GPU-optimized layer substitution can offer 2x-10x speedups, with little to no loss in performance.

Feb 4, 2021

A camel in the desert

Feb 4, 2021

Jonathan Kernes
in
Towards Data Science

Locality Sensitive Hashing: How to Find Similar Items in a Large Set, with Precision

We offer a guide to the art of locality sensitive hashing, with applications to document comparison and vector similarity.

Feb 4, 2021

Locality Sensitive Hashing: How to Find Similar Items in a Large Set, with Precision

Feb 4, 2021

Jonathan Kernes
in
Towards Data Science

SentencePiece Tokenizer Demystified

An in depth dive into the inner workings of the SentencePiece tokenizer, why it’s so powerful, and why it should be your go to tokenizer…

Feb 4, 2021

SentencePiece Tokenizer Demystified

Feb 4, 2021

Jonathan Kernes

Jonathan Kernes

I’m a physics PhD recently taken over by the allure of AI. When I’m not at the computer you might catch me listening to hip hop or watching basketball.

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams