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.
MACHINE LEARNING
-
Robot Grasping: Singulated Objects and Dex-Net Comparison
By
–
Interesting! I'm probably wrong but are all of these examples singulated objects with upward-facing planar surfaces? Curious how it compares with Dex-Net: https://t.co/xGN576WZQU https://t.co/aajdKWx3Nl
— Ken Goldberg (@Ken_Goldberg) 13 novembre 2022Interesting! I'm probably wrong but are all of these examples singulated objects with upward-facing planar surfaces? Curious how it compares with Dex-Net: https://
roboticsbusinessreview.com/news/how-ambid
extrous-plans-to-grow-its-robot-grasping-company/
… -
Infinite Data and Finite Representations of True Distributions
By
–
“Infinite data” means knowing the true distribution, which may have a finite representation. Translating from an infinite representation to an equivalent finite one is not inductive bias.
-
Top Data Science Applications and Technologies Overview
By
–
Top #DataScience Applications
Via @ingliguori #Python #DataScientists #MachineLearning #SQL #Cybersecurity #BigData #Analytics #AI #RStats #TensorFlow #JavaScript #ReactJS #CloudComputing #DataScientist #Linux #Programming #Coding #100DaysofCode #NodeJS #golang #NLP #GitHub -
AI and Society: Deep Learning and Machine Learning Perspectives
By
–
AI & Society Editor : James M. Manyika – https://
amacad.org/sites/default/
files/daedalus/downloads/Daedalus_Sp22_AI-and-Society.pdf
… #ArtificialIntelligence #DeepLearning #MachineLearning -
Pooling and Parameter Sharing: Essential for Translation Invariance in CNNs
By
–
Pooling is a standard part of convnet architecture. Translation invariance is also encoded in parameter sharing: it's the *same* filter you're running across the image (or part of it). Either alone does not do the job.
-
Finite Models and Renormalizability in Quantum Field Theory
By
–
Finite models are always renormalizable. Continuous ones can be easier to handle analytically, but we don't need that today. We have computers. And with guaranteed renormalizability quantum field theory and quantum gravity become easy. What are we waiting for?
-
Universe Turing-Completeness as Fundamental Physical Law
By
–
The first law of physics is that the universe is Turing-complete. Any candidate theory that violates it is empirically false.
-
World Made of Mutual Information: Entropy as Self-Relation
By
–
The world is made of mutual information. Entropy is just a solipsistic instance of it (the mutual information between a variable and itself).
-
Causality as a subtree in the taxonomy of inductive biases
By
–
Agreed. From an ML point of view, there's a taxonomy of inductive biases, and causality is a subtree.