captum VS ml5-library

Most likely, NNs in general love shortcut learning (see Geirhos et al. 2020). In general, local explanations such as grad-cam are quite noisy, and sometimes even inconsistent (see Seo et al. 2018 ). Now, in my experience, I've seen that integrated gradients (see Sundararajan et al 2017) does a better job compared to Grad-CAM (also, add a noise tunnel), but this is only based on my limited experience. I would totally recommend using the implementations from the Captum library for loca explanations.

Take a look at captum

Sometimes. If explainable predictions are part of your business requirements, it's probably better not to rely entirely on black box models and instead design a system that gives you the information you need as part of it. If you end up using black box models, there are still methods that attempt to help attribute explanations to your prediction. Here's an example of a toolkit for attributing explanations post-hoc to black box model predictions: https://github.com/pytorch/captum

The straightforward way to interpret RL agent's decision is to use captum library.

My use-case is research-oriented. I work on Explainable AI. Generally, the best package I've come across to compute attributions in Pytorch Captum. If your object detector is in PyTorch, you can perhaps build it in.

Do any JAX experts know if there is an equivalent to https://captum.ai/ - a model interpretability library for pytorch?

In particular i want to be able to measure feature importance on both inputs and internal layers on a sample by sample basis. This is the only thing currently holding me back from using JAX right now.

Alternatively a simle to read/understand/port implementation of DeepLIFT would work too.

thanks

I'm interested to use JAX but am having a hard time finding anything similar to captum for the pytorch world.

Do you actually want to implement something? There are decent explainability libraries now, e.g., [AIX360](https://aix360.mybluemix.net/), [InterpretML](https://interpret.ml/), or [captum](https://captum.ai/). Pytorch + maybe pytorch lightning + captum might be the quickest way to actually implement something like an explainable neural net yourself. Do the standard tutorials for each of them and watch a few YT videos (or follow a coursera course or something like that) about how these things work in theory and practice, and you'll get up to speed relatively quickly. You will not be able to do useful work in ML without actually learning the ropes.

Important APIs - ml5 for in-browser detection, face-api that uses tensorflow-node to accelerate on-server detection. VueUse for a bunch of useful component tools like the QR Code generator. Yahoo's Gifshot for creating gif files in-browser etc.

> Have we seen any creator of a deep learning library, take a similar position if not stopping any support for anyone using it for mass surveillance?

ml5.js license:

> This license gives everyone as much permission to work with this software as possible as long as they comply with the ml5.js Code of Conduct [...]

ml5.js code of conduct:

> Do not: [...] Use ml5.js to build tools of mass surveillance and prediction to repress the rights of people

https://github.com/ml5js/ml5-library/blob/main/LICENSE.md

Not sure how enforcable this is but it exists.

See also: https://ml5js.org/

"The library provides access to machine learning algorithms and models in the browser, building on top of TensorFlow.js with no other external dependencies."

(5) ml5.js

ML.js

I used ml5js.org , p5js.org and https://teachablemachine.withgoogle.com to train the Banana images. When you create a new image project on Teachable Machine, you can output the p5js and basically use it right out of the box - I customized js, css, and html from there.

Going forward: I'll be 100% into JavaScript. You can use JavaScript in so many fields nowadays. Websites React, Mobile Apps React Native, Machine Learning TensorFlow & ML5, Desktop Applications Electron, and of course the backend Node as well. It's kind of a no-brainer. Of course, they all have specific languages that are better, but for now, JavaScript is a bit of a catch-all.

Yeah they made ml5.js for this reason: https://ml5js.org/

I do feel like Google could do better communicating all of their different tools though. Their ecosystem is large and pretty confusing - they've got so many projects going on at once that it always seems like everyone gets fed up with them before they take a second pass and make them more friendly to newcomers.

Facebook seems to have taken a much more focused approach as you can see with PyTorch Live

From other comments, a lot of JavaScript developers who want to use TensorFlow had never heard of TensorFlow.js or ml5.js!