Combining Fast and Slow Thinking for Human-like and Efficient Navigation in Constrained Environments Ganapini et al.: https://
arxiv.org/abs/2201.07050 #ArtificialIntelligence #DeepLearning #MachineLearning
MACHINE LEARNING
-
Fast and Slow Thinking for Autonomous Robot Navigation
By
–
-
ChatGPT correctly answers Super Bowl question about Justin Bieber’s birth year
By
–
Here's a related tweet, from the pre-ChatGPT era. Nowadays, ChatGPT can correctly answer the question, "What NFL team won the Super Bowl in the year Justin Bieber was born?" without any CoT prompting, unlike prior GPT-3 versions.
-
NeurIPS Summary with Incorrect Acceptance Rate
By
–
Summary of NeurIPS, complete with wrong acceptance rate.
-
New Protocol Evaluates Machine Learning Model Input Salience Methods
By
–
#MachineLearning models sometimes make correct predictions by using information that is irrelevant to the task. Learn more about a new protocol for evaluating input salience methods, which can help verify that a model isn’t relying on such information → https://
goo.gle/3gZSOWl -
MIT Cheetah robot learns soccer through machine learning
By
–
How MIT's mini Cheetah #robot learns to play soccerhttps://t.co/2QKoukxPlU @BBC#Robots #AI @FrRonconi @mvollmer1 @YvesMulkers @Khulood_Almani @JAdP @BetaMoroney @PawlowskiMario @Fabriziobustama @enilev @CurieuxExplorer @CurieuxExplorer @FmFrancoise @Nicochan33 @CatherineAdenle pic.twitter.com/ZQXctoxkdD
— Marcus Borba (@marcusborba) 6 décembre 2022How MIT's mini Cheetah #robot learns to play soccer https://
youtube.com/watch?v=_vR-38
NcHtM
… @BBC #Robots #AI @FrRonconi @mvollmer1 @YvesMulkers @Khulood_Almani @JAdP @BetaMoroney @PawlowskiMario @Fabriziobustama @enilev @CurieuxExplorer @CurieuxExplorer @FmFrancoise @Nicochan33 @CatherineAdenle -
Meta AI’s CICERO: Training, Dialogue Integration, and Trust Building
By
–
Meta AI’s @adamlerer speaks to the challenges faced in creating #CICERObyMetaAI — from training on millions of Diplomacy moves, to integrating human dialogue & understanding w/ the purpose of enabling CICERO to build trust w/ other players.
-
AWS DEI and Responsible AI: ML Explainability and Bias Reduction
By
–
A #DEI & Responsible #AI #reInvent session spotlight! @awscloud https://
youtu.be/PJMsL_pyd5o @YouTube From #ML #explainability & #innovation to reduce #bias to fantastic #AWS #skills Scholarship ! #tech #partner @Shi4Tech #100DaysOfCode @EvaSmartAI @ipfconline1 @domhalps #IoT -
LLMs Excel at Poetry Through Statistical Pattern Recognition
By
–
(imo simple poem crafting is right in the thick of Moravec's paradox – difficult for humans to generate but quite tractable for an LLM to keep track of the statistics of all the possible words and how they rhyme)
-
Geoffrey Hinton Birthday: Godfather of AI Neural Networks
By
–
Happy birthday to Geoffrey Hinton, whose work in neural networks has led many to call him the “Godfather of AI": https://
bit.ly/3uz6nik @Telegraph -
Autoregressive Search Engines: Generating Substrings as Document Identifiers
By
–
Autoregressive Search Engines: Generating Substrings as Document Identifiers https://
bit.ly/3VRHjio 5/6