AI - AI Dynamics

Need for Comprehensive Inductive Bias Zoo Reference

By

–

14 November 2022 6h18

I cover the highest levels in "The Master Algorithm". Below that there are subfield-specific ones. But someone should really do a serious Inductive Bias Zoo, a la Scott Aaronson's Complexity Zoo.

→ View original post on X — @pmddomingos

14 November 2022

AI-Powered Exosuit Restores Mobility for MS and Stroke Patients

By

@pascal_bornet

–

14 November 2022 6h06

Amazing results for multiple sclerosis patient Louisa, after 1 hour. Improving the #mobility of people affected by strokes or Parkinson’s disease

The suit is equipped with 58 embedded #electrodes, which are adjusted to the user’s body

Crt: Ottobock #innovation #techforgood #ai pic.twitter.com/xPBM0ARzGK
— Pascal Bornet (@pascal_bornet) 14 novembre 2022

Amazing results for multiple sclerosis patient Louisa, after 1 hour. Improving the #mobility of people affected by strokes or Parkinson’s disease The suit is equipped with 58 embedded #electrodes, which are adjusted to the user’s body Crt: Ottobock #innovation #techforgood #ai

→ View original post on X — @pascal_bornet

14 November 2022

Causal Theories as Inductive Bias in Machine Learning

By

@pmddomingos

–

14 November 2022 5h05

On the contrary: it's by viewing causal theories as a type of inductive bias that ML types can become comfortable with using them. (As I said before, there's a taxonomy of inductive biases; by placing a bias in the appropriate node you don't confuse, you clarify.)

→ View original post on X — @pmddomingos

14 November 2022

Contrived Datasets and Knowledge Transfer in Causal Analysis

By

@pmddomingos

–

14 November 2022 5h00

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.

→ View original post on X — @pmddomingos

14 November 2022

Malicious Use of AI: Forecasting, Prevention, and Mitigation

By

@montreal_ai

–

14 November 2022 4h56

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

→ View original post on X — @montreal_ai

14 November 2022

Guided Image Inpainting for Video Object Removal

By

@learnopencv

–

14 November 2022 4h29

Ever wondered how object removal can be done on a video?
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/TWgsUFdf4L
— Satya Mallick (@LearnOpenCV) 14 novembre 2022

Ever 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

→ View original post on X — @learnopencv

14 November 2022

Learning Causality Does Not Require Different Training and Test Domains

By

@pmddomingos

–

14 November 2022 1h36

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.

→ View original post on X — @pmddomingos

14 November 2022

Machine Learning Model for Soldier Casualty Prediction from Shot Data

By

@pmddomingos

–

14 November 2022 1h29

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.

→ View original post on X — @pmddomingos

14 November 2022