Webinar Recap: Data Augmentation

The Jaxon team hosted a webinar covering Data Augmentation where we discussed what data augmentation is, how it works for images, how it works for text, and why text augmentation is so much more difficult than image augmentation:http://www.jaxon.ai/wp-content/uploads/2020/07/Edited-Data-Augmentation-Webinar-07172020_1.mp4…

Comments Off on Webinar Recap: Data Augmentation

Towards Unified Machine Learning

Let's break applied machine learning problems down into simple taxonomy. These problems can be classified according to a (non-exhaustive) two-dimensional model: data type and problem type: Data TypesText (Natural Language)ImagesTabularVideoSensor/Time-SeriesProblem TypesClassificationRegressionInformation ExtractionTransformation (seq2seq, generative)We can even plot the intersection…

Comments Off on Towards Unified Machine Learning

The Egg and the Chicken

When people first learn about Jaxon, a common question is how we are able to train a model to produce data that will train a better model. Isn't that first model already the model we want if it…

Comments Off on The Egg and the Chicken

The Puzzle Pitfalls of Building ML Pipelines

In an ideal world, machine learning pipelines would build themselves. As it sits though, this tedious process currently falls on the shoulders of data scientists and engineers. As noted in “The Gotchas of ML/NLP”, the key to successfully…

Comments Off on The Puzzle Pitfalls of Building ML Pipelines

“Do You Even Lift?” – A Jaxon Guide to Training Classifiers

Once you've used Jaxon to label your training set and you're ready to embark on training classifiers, it would seem that you’re in the home stretch and there’s not much more work to be done. However, to obtain a high-performing classifier,…

Comments Off on “Do You Even Lift?” – A Jaxon Guide to Training Classifiers

Fast Track to Gold

I first read about Lean Thinking in the book The Machine That Changed the World, based on MIT’s $5M, five-year study on the future of auto manufacturing. The concept of ‘lean’ embraces ideas like just-in-time delivery, elimination of waste…

Comments Off on Fast Track to Gold

Just Enough Human Supervision

We had hubris a couple years ago, thinking you can create accurate machine learning (ML) models completely unsupervised. Turns out, some human supervision really is needed. Just enough human knowledge to train the model properly. The trick is…

Comments Off on Just Enough Human Supervision

The ‘Gotchas’ of ML/NLP

Building machine learning models can be exhilarating - finding that optimal combination of technologies and piecing them together into a final, smooth end result gives a unique sense of accomplishment that only data scientists and engineers really understand.…

Comments Off on The ‘Gotchas’ of ML/NLP

Dazed and Confused

So you've trained yourself a machine learning classifier. You want to tweet it (or whatever the kids do these days) to the world! Print out a copy of the weight matrix for Mom to hang on the fridge.…

Comments Off on Dazed and Confused

Why Use AI to Label Data?

Why use AI to label data? Long story short, humans are slow.When humans are labeling text - for example reading a tweet and deciding if it demonstrates positive or negative sentiment - the whole process takes at least…

Comments Off on Why Use AI to Label Data?

End of library

No more resources to load