Trusting Machine Learning Models with LIME
Data Skeptic19 Elo 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.

Tämä jakso on lisätty Podme-palveluun avoimen RSS-syötteen kautta eikä se ole Podmen omaa tuotantoa. Siksi jakso saattaa sisältää mainontaa.

Jaksot(601)

[MINI] Natural Language Processing

[MINI] Natural Language Processing

This episode overviews some of the fundamental concepts of natural language processing including stemming, n-grams, part of speech tagging, and th bag of words approach.

17 Huhti 201513min

Computer-based Personality Judgments

Computer-based Personality Judgments

Guest Youyou Wu discuses the work she and her collaborators did to measure the accuracy of computer based personality judgments. Using Facebook "like" data, they found that machine learning approaches...

10 Huhti 201531min

[MINI] Markov Chain Monte Carlo

[MINI] Markov Chain Monte Carlo

This episode explores how going wine testing could teach us about using markov chain monte carlo (mcmc).

3 Huhti 201515min

[MINI] Markov Chains

[MINI] Markov Chains

This episode introduces the idea of a Markov Chain. A Markov Chain has a set of states describing a particular system, and a probability of moving from one state to another along every valid connected...

20 Maalis 201511min

Oceanography and Data Science

Oceanography and Data Science

Nicole Goebel joins us this week to share her experiences in oceanography studying phytoplankton and other aspects of the ocean and how data plays a role in that science.   We also discuss Thinkful ...

13 Maalis 201533min

[MINI] Ordinary Least Squares Regression

[MINI] Ordinary Least Squares Regression

This episode explores Ordinary Least Squares or OLS - a method for finding a good fit which describes a given dataset.

6 Maalis 201518min

NYC Speed Camera Analysis with Tim Schmeier

NYC Speed Camera Analysis with Tim Schmeier

New York State approved the use of automated speed cameras within a specific range of schools. Tim Schmeier did an analysis of publically available data related to these cameras as part of a project a...

27 Helmi 201516min

[MINI] k-means clustering

[MINI] k-means clustering

The k-means clustering algorithm is an algorithm that computes a deterministic label for a given "k" number of clusters from an n-dimensional datset.  This mini-episode explores how Yoshi, our lilac c...

20 Helmi 201514min

Suosittua kategoriassa Tiede

rss-mita-tulisi-tietaa
rss-poliisin-mieli
tiedekulma-podcast
menologeja-tutkimusmatka-vaihdevuosiin
sotataidon-ytimessa
filocast-filosofian-perusteet
rss-duodecim-lehti
rss-astetta-parempi-elama-podcast
rss-lapsuuden-rakentajat-podcast
utelias-mieli
docemilia
radio-antro
rss-ranskaa-raakana
rss-kasvatuspsykologiaa-kaikille
rss-tiedetta-vai-tarinaa
rss-luontopodi-samuel-glassar-tutkii-luonnon-ihmeita
rss-sosiopodi