Scott Lundberg, Microsoft Research - Explainable Machine Learning with Shapley Values -

  Рет қаралды 26,938

H2O.ai

H2O.ai

Күн бұрын

Пікірлер: 4
@abdelbaki8625
@abdelbaki8625 7 ай бұрын
i dont understand how calculate shap value
@julianocamargo6674
@julianocamargo6674 4 жыл бұрын
Great presentation, thanks!
@Malbao14
@Malbao14 4 жыл бұрын
I have a question that I'm facing today. When seeing with shap that you model does not behave like you want it to (like in 14:30 in the video), how can we force this change on the model?
@naveen3046
@naveen3046 4 жыл бұрын
Hi sir, I like to share my opinion. This problem is related to our model. So It can be solved by focusing on the data set that we have, collecting more data relevant to that feature, we need to teach our model how to analyze that feature, Changing the model may help. My opinion is that this like problems are relevant to our data set, and model. I too experienced this problem, then I collected data which mainly focus on those features and then designed my model again. It helped little bit to solve. Thank you
05e Machine Learning: Shapley Value
37:29
GeostatsGuy Lectures
Рет қаралды 16 М.
How to have fun with a child 🤣 Food wrap frame! #shorts
0:21
BadaBOOM!
Рет қаралды 17 МЛН
БОЙКАЛАР| bayGUYS | 27 шығарылым
28:49
bayGUYS
Рет қаралды 1,1 МЛН
GraphRAG: The Marriage of Knowledge Graphs and RAG: Emil Eifrem
19:15
Why LLMs Are Going to a Dead End Explained | AGI Lambda
14:46
AGI Lambda
Рет қаралды 4,4 М.
The mathematics behind Shapley Values
11:48
A Data Odyssey
Рет қаралды 33 М.
The Science Behind InterpretML: SHAP
11:46
Microsoft Developer
Рет қаралды 51 М.
Why Does Diffusion Work Better than Auto-Regression?
20:18
Algorithmic Simplicity
Рет қаралды 401 М.
How to have fun with a child 🤣 Food wrap frame! #shorts
0:21
BadaBOOM!
Рет қаралды 17 МЛН