Kerry Champion (@MenloML) header
Kerry Champion (@MenloML) profile picture

Let's make AI more trustworthy, verifiable and explainable.

Palo Alto, CA
Joined December 2017
Photo by Kerry Champion (@MenloML)Photo by Kerry Champion (@MenloML)Photo by Kerry Champion (@MenloML)Photo by Kerry Champion (@MenloML)Photo by Kerry Champion (@MenloML)Photo by Kerry Champion (@MenloML)Photo by Kerry Champion (@MenloML)Photo by Kerry Champion (@MenloML)Photo by Kerry Champion (@MenloML)Photo by Kerry Champion (@MenloML)
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.
13
145
27
658
Kerry Champion retweeted
A deer must have lost its keys. ⁦@EconTalker⁩
4
1
28
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-…
1
2
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…
"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.
2
2
1
18
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.
3
3
1
32
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:
10
139
24
323
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…
"Aucun algorithme non explicable ne pourra être utilisé par l'administration"; et aucun algorithme en matière de condamnations judiciaires, promet @mounir. #RGPD #DirectAN
3
19
3
34
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.
3
13
3
105
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.
18
299
50
1,027
#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