Designing, building, and training models are hard problems. Literature is reviewed, data is gathered (and cleaned and annotated). Hours (or perhaps days? weeks?) are spent getting code to work, fixing subtle bugs, tuning training schemes. Finally, the met... (more…)

Once you’ve built a machine learning classifier, the next step is to validate it and see how well it fits the data. This short post will list the common metrics we can use to evaluate a classifier.… (more…)

🤖 Interactive Machine Learning experiments: 🏋️models training + 🎨models demo - trekhleb/machine-learning-experiments... (more…)

How Teleport uses AI to peak into every street corner...

In Harvard's Nuremberg Trials Project, being able to link to cited documents in each trial's transcript is a key feature of site navigation. Each doc... (more…)