I Spent May Evaluating Different Engines for OCR
were supposed to be read by a machine. Old hotel invoices, bank statements, payslips, loan…
A Discussion of ‘Adversarial Examples Are Not Bugs, They Are Features’
On May 6th, Andrew Ilyas and colleagues published a paper outlining two sets of experiments.…
Mocking a Year of IoT Sensor Time Series Data with Mimesis
# Introduction Mocking Internet of Things (IoT) sensor data that would be otherwise difficult to…
Solving a Murder Mystery Using Bayesian Inference
I remember watching the Hollywood mystery thriller Knives Out, leaning towards the screen, as if…
A Discussion of ‘Adversarial Examples Are Not Bugs, They Are Features’: Discussion and Author Responses
We want to thank all the commenters for the discussion and for spending time designing…
Practical NLP in the Browser with Transformers.js
# Introduction For a long time, running transformer models meant maintaining a Python server, paying…
EmoNet: Speaker-Aware Transformers for Emotion Recognition — and What I’d Build Differently in 2026
, I submitted my MS thesis on Emotion Recognition in Conversation (ERC). The model, EmoNet, achieved…
Adversarial Example Researchers Need to Expand What is Meant by ‘Robustness’
The hypothesis in Ilyas et. al. is a special case of a more general principle…
Visual Debugging Tools for Machine Learning Workflows
# Introduction Training a machine learning model and observing the loss decrease is a feeling…