Kerry Champion retweeted
In statistics, a small sample often gives a weird result, especially if the samples aren't independent. A family is a small, non-independent sample of the population. This is why your family is so weird.
Kerry Champion retweeted
A deer must have lost its keys. @EconTalker
If you are in Tokyo and are interested in #ExplainableAI and the benefits of opening up the machine learning #blackbox this is the meetup for you.
#XAI #InterpretableML
meetup.com/Machine-Learning-…
What Cloudera is missing about automating decisions? In complex consequential cases we won't fully automate our decision making. Rather we will build Human-AI hybrid systems.
#ExplainableAI #EnterpriseAI #MachineLearning xai.world/2018/03/14/what-cl…
Increasingly we will see a Human/AI hybrid approach to knowledge work. Whether it is for journalists, lawyers or sub captains this approach inherently requires opening AI's black box.
#ExplainableAI #EnterpriseAI #MachineLearning xai.world/2018/03/13/ai-deci…
1
Lessons from Airbnb pricing system. Decision support vs. automated decision making. Model performance metrics vs. enterprise system utility.
#MachineLearning #ExplainableAI #EnterpriseAI xai.world/2018/03/01/airbnb-…
1
Three reasons to not sacrifice interpretability to gain #MachineLearning model metric performance.
#ExplainableAI #EnterpriseAI xai.world/2018/02/27/perform…
The search for spy planes illustrates how #ExplainableAI can improve the generalizability and robustness of our #MachineLearning systems.
#AI #EnterpriseAI xai.world/2018/02/26/the-sea…
Kerry Champion retweeted
"Interpretability slows down ML adoption"
Model-agnostic tools also invalidate this argument. It is also contraire to my experiences from jobs, consulting and dozens of conversations with practitioners and statisticians: LACK of interpretability is slowing down adoption.
Kerry Champion retweeted
Performance > Interpretability
True, if you can capture 100% of your problem's definition in a single loss function, the training data was collected in controlled setting, and you do not care to learn anything about the problem.
An unlikely situation.
Kerry Champion retweeted
Most common arguments against interpretable ML:
- Humans can't explain their actions either
- Performance > Interpretability
- Slows down ML adoption
- Linear model also not interpretable
- Might create illusion of understanding the model
Thread:
Google Clips allow users to look a bit below the ‘water line’ and illustrates the value of a 'contrastive explanation' that communicates boundary conditions.
#ExplainableAI #MachineLearning #AIUX xai.world/2018/02/22/xai-les…
Kerry Champion retweeted
The #ExplainableAI wave reaches France (think I remember an AINow report advised this?) cc @katecrawford @FrankPasquale
"Any algorithm that can't be explained can't be used by the civil service" promises France's digital minister Mounir Mahjoubi in French parliament [RGPD = GDPR] xitter.gq/gchampeau/status/96135…
We are starting to see algos that work with semantically meaningful features (explicit or latent) and address two of Peter's drivers: make training more efficient and improve explainability.
xai.world/2018/02/19/semanti… xitter.gq/PeterHeywood_/status/9…
Taking a human centered approach to #MachineLearning and integrating a cross functional team are both easier when taking an #ExplainableAI approach.
#EnterpriseAI
menloml.com/2018/02/21/need-…
Kerry Champion retweeted
I think that's the key: we don't often know the right question to ask when we start a line of empirical inquiry. We refine some initial vague set of question as we interact with data, answer some of them, and generate new ones.
Kerry Champion retweeted
I'm as enthusiastic about the future of AI as (almost) anyone, but I would estimate I've created 1000X more value from careful manual analysis of a few high quality data sets than I have from all the fancy ML models I've trained combined.
#MachineLearning models can lead to serendipitous discoveries. #XAI techniques can help us distinguish between misleading coincidental correlations and genuine new insights.
#ExplainableAI xai.world/2018/02/19/serendi…
Three current #MachineLearning techniques that produce benefits from generating semantically meaningful features.
#xAI #EnterpriseAI xai.world/2018/02/19/semanti…
1















