But in reality you may fail when you try to do f(X), so doing it is effectively just another perturbation, albeit under your control.
RESEARCH
-
Rung 3 Model: Conditioning on Evidence and Counterfactuals
By
–
All rung 3 requires is a model that lets you condition on arbitrary evidence, including counterfactuals. To learn the model you need inductive biases / prior assumptions, which are necessary and sufficient for all rungs and may or may not include a theory of causality.
-
Permutation Invariance: Operating on Unordered Sets
By
–
Permutation invariance lets you operate on (unordered) sets. It's not a symbol manipulation apparatus per se.
-
Algorithms for Learning Symmetries Save Data in Machine Learning
By
–
We have algorithms for learning symmetries, and using them saves a lot of data. E.g.: https://
homes.cs.washington.edu/~pedrod/papers
/nips14.pdf
… -
32 Years Since WorldWideWeb Proposal by Berners-Lee Cailliau
By
–
32 years ago today Tim Berners-Lee and Robert Cailliau emailed colleagues outlining a proposal for a hypertext project that they dubbed "WorldWideWeb." https://
w3.org/Proposal.html (v/@w3c) #tdih #todayintech #WWW -
Funding AGI Research Through Commercial Products and Business
By
–
What's wrong with selling products and doing business in order to fund important research? This is what we've been doing since 20 years at http://
MONTREAL.AI : we never wanted ANY external funding #AGI #MontrealAI -
System of Constrained Policy Optimization in Machine Learning
By
–
System of Constrained Policy Optimization. @rachelevagordon #BigData #Analytics #DataScience #AI #MachineLearning #IoT #IIoT #Python #RStats #TensorFlow #JavaScript #ReactJS #GoLang #Serverless #DataScientist #Linux #Programming #Coding #100DaysofCode https://
bit.ly/3hFaMNx -
Alan Turing Defined Computing 85 Years Ago Today
By
–
Alan Turing first defined what’s now the Turing Machine 85 years ago #otd, shaping how machines compute info. today: http://
bit.ly/2zz5Lik Image v/Godrey Argent Studio & The Royal Society -
Learning from Failure Stories More Effective Than Success
By
–
Interestingly, stories of failure may be more useful for learning. They can be more easily applied than stories of success, especially if the story is interesting and you believe that it is important to learn from mistakes. Just be sure the story is true! https://
ink.library.smu.edu.sg/cgi/viewconten
t.cgi?article=1021&=&context=lkcsb_research_all&=&sei-redir=1&referer=https3A2F2Fscholar.google.com2Fscholar3Fhl3Den26as_sdt3D0252C3926q3Dlearning2Bfrom2Bothers2Bfailure26btnG3D#search=learningfromothersfailure
… -
AI Today Podcast: AGI, Strong AI, Narrow AI Definitions
By
–
In this @Cognilytica #AIToday AI Glossary Series #podcast episode 'Artificial General Intelligence (AGI), Strong AI, Weak AI, Narrow AI' hosts @rschmelzer & @kath0134 share the definitions for AGI/Strong AI and Narrow/Weak AI. Full episode: https://
cognilytica.com/2022/11/11/ai-
today-podcast-ai-glossary-series-artificial-general-intelligence-agi-strong-ai-weak-ai-narrow-ai/?utm_source=dlvr.it&utm_medium=twitter
… #tech #AGI #AI