That's a very contrived data set, which makes it very unpersuasive. You then have to transfer knowledge to this problem from similar ones with better data, which is what the "causal bias" is really doing.
RESEARCH
-
Malicious Use of AI: Forecasting, Prevention, and Mitigation
By
–
The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation Brundage and Avin et al. https://
img1.wsimg.com/blobby/go/3d82
daa4-97fe-4096-9c6b-376b92c619de/downloads/MaliciousUseofAI.pdf?ver=1553030594217
… #ArtificialIntelligence #DeepLearning #MachineLearning -
Guided Image Inpainting for Video Object Removal
By
–
Ever wondered how object removal can be done on a video?
— Satya Mallick (@LearnOpenCV) 14 novembre 2022
Here is an interesting one on Guided Image Inpainting
Paper: https://t.co/I1SBGjzEgh
Code: https://t.co/ssHayfP8EW #learnopencv #opencv #computervision #github #artificialintelligence #deeplearning #machinelearning #ai pic.twitter.com/TWgsUFdf4LEver wondered how object removal can be done on a video?
Here is an interesting one on Guided Image Inpainting Paper: https://
arxiv.org/pdf/2204.07845
.pdf
… Code: https://
github.com/runwayml/guide
d-inpainting
… #learnopencv #opencv #computervision #github #artificialintelligence #deeplearning #machinelearning #ai -
Learning Causality Does Not Require Different Training and Test Domains
By
–
Surely showing you can learn (what looks like) causality does not require the training and test examples to be in different domains. That's an orthogonal issue.
-
Machine Learning Model for Soldier Casualty Prediction from Shot Data
By
–
Easy. The data is vectors of "shot/not shot" (one input variable per soldier) and "dead/alive" (output). Any learner that induces that num. shots > 0 => dead answers the question correctly.
-
Postdoc Position in Surgical AI at Caltech
By
–
Come and work with me and @AjhungMD as a postdoc in Surgical AI https://
cms.caltech.edu/about/position
s/surgicalai
… -
Inductive Biases in Machine Learning: Beyond Curve-Fitting
By
–
1. Many inductive biases aren’t curve-fitting (e.g., ILP, causal theories).
2. You can’t learn at any level without inductive biases.
3. We also call everything that doesn’t work “inductive biases”. ML is the search for the ones that do, in any form. -
Machine Learning Progress with Minimal Data and Inductive Biases
By
–
Indeed, but the interesting ML question is how far you can get with how little. Find the right inductive biases, and you could get very far very quickly.
-
François Chollet Launches Sparks in the Wind Newsletter on Education
By
–
I'm starting a newsletter. It's called "Sparks in the Wind": mostly ephemeral random thoughts — but with a small chance of starting a fire. Posts are going to be similar to my Twitter threads, but longer and more polished. First post is on education: https://
fchollet.substack.com/p/education-as
-civilization-building
… -
Explainable AI and Trust in Artificial Intelligence Conversations
By
–
Explaining Explainable AI for Conversations: Something is missing in artificial intelligence – trust. https://
kdnuggets.com/2022/10/explai
ning-explainable-ai-conversations.html?utm_source=dlvr.it&utm_medium=twitter&utm_campaign=explaining-explainable-ai-for-conversations
…