WearableIntelligenceSystem VS interpret

This architecture is pretty much what we've built out as a smart glasses software framework here: https://github.com/emexlabs/WearableIntelligenceSystem

Smart glasses are a novel interface in a few key ways. Most obviously, they bring the screen directly in front of the user, so they are able to access a visual information stream at all times. Not as commonly thought-about, but perhaps more important, is the access to always on point-of-view (POV) sensory data. This allows the machine to "see what you see" and "hear what you hear". The video above is a quick display of a few basic features that smart glasses can provide. We'd love to know where you see this technology going? Of course spatial computing and AR is cool and hype now, but what use cases do you think you'll use in your everday life? What could enhance your intelligence and capabilities by taking advantage of this new form factor? We're trying to answer these questions, and building a system that makes it easy for developers to build their own smart glasses applications: https://github.com/emexlabs/WearableIntelligenceSystem

Also, the Open Source smart glasses software stack Wearable Intelligence System has this transcription/translation built-in: https://github.com/emexlabs/WearableIntelligenceSystem

Here's the open source system: https://github.com/emexlabs/WearableIntelligenceSystem

Soon there will be! I am working with a team right now to develop an app for smart glasses that I am designing in a way that will help me with my ADHD. Here's the project.

We're trying to answer these questions, and building a system that makes it easy for developers to build their own smart glasses applications: https://github.com/emexlabs/WearableIntelligenceSystem

Maybe InterpretML? It's developed and maintained by Microsoft Research and consolidates a lot of different explainability methods.

You may also find Explainable Boosting Machines interesting: https://github.com/interpretml/interpret

They're a bit like a best of both worlds between linear models and random forests (generalized additive models fit with boosted decision trees)

Disclosure: I helped build this open source package

Microsoft Explainable Boosting Machine (which is a Gaussian Additive Model and not a Gradient Boosted Trees 🙄 model) is a step in that direction https://github.com/interpretml/interpret

Also I'd recommend everyone who works with xgboost to give EBM's a try! They perform comparably (except in the case of extreme interactions) but are actually interpretable! https://github.com/interpretml/interpret/ Beside that they since on runtime they're practically a lookup table they're very quick (at the cost of longer training time).

Open source code by Microsoft: https://github.com/interpretml/interpret (called EBM in this implementation).

If it's not an image, have a go at Microsoft's Explainable Boosting Maching) https://github.com/interpretml/interpret which is not a GBM but a GAM (Gradient Boosting Machine vs Gradient Additive Model). This will also give you explanation via SHAP or LIME values.