Trusting Machine Learning Models with LIME
Data Skeptic19 Aug 2016

Trusting Machine Learning Models with LIME

Machine learning models are often criticized for being black boxes. If a human cannot determine why the model arrives at the decision it made, there's good cause for skepticism. Classic inspection approaches to model interpretability are only useful for simple models, which are likely to only cover simple problems.

The LIME project seeks to help us trust machine learning models. At a high level, it takes advantage of local fidelity. For a given example, a separate model trained on neighbors of the example are likely to reveal the relevant features in the local input space to reveal details about why the model arrives at it's conclusion.

In this episode, Marco Tulio Ribeiro joins us to discuss how LIME (Locally Interpretable Model-Agnostic Explanations) can help users trust machine learning models. The accompanying paper is titled "Why Should I Trust You?": Explaining the Predictions of Any Classifier.

Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(601)

Bird Distribution Modeling with Satbird

Bird Distribution Modeling with Satbird

This episode features an interview with Mélisande Teng, a PhD candidate at Université de Montréal. Her research lies in the intersection of remote sensing and computer vision for biodiversity monitori...

10 Sep 202439min

Ant Encounters

Ant Encounters

In this interview with author Deborah Gordon, Kyle asks questions about the mechanisms at work in an ant colony and what ants might teach us about how to build artificial intelligence. Ants are surpri...

26 Aug 202431min

Computing Toolbox

Computing Toolbox

This season it's become clear that computing skills are vital for working in the natural sciences. In this episode, we were fortunate to speak with Madlen Wilmes, co-author of the book "Computing Skil...

19 Aug 202438min

Biodiversity Monitoring

Biodiversity Monitoring

In this episode, we talked shop with Hager Radi about her biodiversity monitoring work. While biodiversity modeling may sound simple, count organisms and mark their location, there is a lot more to it...

14 Aug 202432min

Hacking the Colony

Hacking the Colony

Today, Ashay Aswale and Tony Lopez shared their work on swarm robotics and what they have learned from ants. Robotic swarms must solve the same problems that eusocial insects do. What if your pheromon...

8 Aug 202441min

Primate Poses

Primate Poses

During this season we have talked with researchers working to utilize machine learning for behavioral observations. In previous episodes, you have heard about the software people like Richard use, but...

31 Jul 202432min

Generating 3D Animals with YouDream

Generating 3D Animals with YouDream

Generative AI can struggle to create realistic animals and 2D representations often have mistakes like extra limbs and tails. If 2D wasn't hard enough, there are researchers working on generative 3D m...

23 Jul 20241h

Weird Communication

Weird Communication

Today, we sat down with Dr. Ignacio Escalante Meza to learn about opiliones and treehoppers. Opiliones, known as "daddy long legs" in the US, are understudied arachnids known for their tenacious locom...

15 Jul 202438min

Populært innen Vitenskap

fastlegen
jss
tingenes-tilstand
forskningno
rekommandert
rss-paradigmepodden
villmarksliv
sinnsyn
rss-zahid-ali-hjelper-deg
vett-og-vitenskap-med-gaute-einevoll
kvinnehelsepodden
rss-inn-til-kjernen-med-sunniva-rose
nordnorsk-historie
nevropodden
tidlose-historier
liberal-halvtime
fjellsportpodden
rss-overskuddsliv
grunnstoffene
rss-rekommandert