cm0002@lemmy.worldEnglish · 7 days agoThe Attention Mechanism Born for Cost Optimizationplus-squareoilbeater.comexternal-linkmessage-square1linkfedilinkarrow-up15arrow-down10
arrow-up15arrow-down1external-linkThe Attention Mechanism Born for Cost Optimizationplus-squareoilbeater.comcm0002@lemmy.worldEnglish · 7 days agomessage-square1linkfedilink
cm0002@lemmy.worldEnglish · 9 days agodcdaML - devanagari character detection dataset training frameworkplus-squaregithub.comexternal-linkmessage-square0linkfedilinkarrow-up13arrow-down10
arrow-up13arrow-down1external-linkdcdaML - devanagari character detection dataset training frameworkplus-squaregithub.comcm0002@lemmy.worldEnglish · 9 days agomessage-square0linkfedilink
cm0002@lemmy.worldEnglish · 15 days agoNeural Graffiti is an experiment in adding a "Spray Layer" to a transformer model, which injects a memory trace into the final stages of inference without finetuning or retrainingplus-squaregithub.comexternal-linkmessage-square0linkfedilinkarrow-up14arrow-down12
arrow-up12arrow-down1external-linkNeural Graffiti is an experiment in adding a "Spray Layer" to a transformer model, which injects a memory trace into the final stages of inference without finetuning or retrainingplus-squaregithub.comcm0002@lemmy.worldEnglish · 15 days agomessage-square0linkfedilink
kerntucky@infosec.pubEnglish · 2 months agoMalicious ML models found on Hugging Face Hubplus-squarewww.helpnetsecurity.comexternal-linkmessage-square0linkfedilinkarrow-up19arrow-down12
arrow-up17arrow-down1external-linkMalicious ML models found on Hugging Face Hubplus-squarewww.helpnetsecurity.comkerntucky@infosec.pubEnglish · 2 months agomessage-square0linkfedilink
Charlie Fish@eventfrontier.comEnglish · 3 months agoVery inconsistent machine learning model trainingplus-squaremessage-squaremessage-square17linkfedilinkarrow-up18arrow-down11
arrow-up17arrow-down1message-squareVery inconsistent machine learning model trainingplus-squareCharlie Fish@eventfrontier.comEnglish · 3 months agomessage-square17linkfedilink
Charlie Fish@eventfrontier.comEnglish · 6 months agocoremltools Error: ValueError: perm should have the same length as rank(x): 3 != 2plus-squaremessage-squaremessage-square0linkfedilinkarrow-up13arrow-down10
arrow-up13arrow-down1message-squarecoremltools Error: ValueError: perm should have the same length as rank(x): 3 != 2plus-squareCharlie Fish@eventfrontier.comEnglish · 6 months agomessage-square0linkfedilink
Charlie Fish@eventfrontier.comEnglish · 6 months agoTensorFlow Lemmy Communityplus-squareeventfrontier.comexternal-linkmessage-square2linkfedilinkarrow-up110arrow-down10
arrow-up110arrow-down1external-linkTensorFlow Lemmy Communityplus-squareeventfrontier.comCharlie Fish@eventfrontier.comEnglish · 6 months agomessage-square2linkfedilink
Shamar@feddit.itEnglish · 6 months agoA community statement supporting the Open Source Definition (OSD)plus-squareosd.fyiexternal-linkmessage-square1linkfedilinkarrow-up17arrow-down12
arrow-up15arrow-down1external-linkA community statement supporting the Open Source Definition (OSD)plus-squareosd.fyiShamar@feddit.itEnglish · 6 months agomessage-square1linkfedilink
tomjuggler@lemmy.worldEnglish · 1 year agoAlternative to Generating images: get AI to generate query for real image (Unsplash)plus-squaremessage-squaremessage-square3linkfedilinkarrow-up117arrow-down13
arrow-up114arrow-down1message-squareAlternative to Generating images: get AI to generate query for real image (Unsplash)plus-squaretomjuggler@lemmy.worldEnglish · 1 year agomessage-square3linkfedilink
keepthepace@slrpnk.netEnglish · 1 year agoWho else here loves the end-to-end robotics model that seem to go out on a weekly basis?twitter.comexternal-linkmessage-square2linkfedilinkarrow-up110arrow-down13
arrow-up17arrow-down1external-linkWho else here loves the end-to-end robotics model that seem to go out on a weekly basis?twitter.comkeepthepace@slrpnk.netEnglish · 1 year agomessage-square2linkfedilink
taaz@biglemmowski.winEnglish · edit-21 year agoModel Design Theory Tips/Tricks/Docs (for a card game agent)plus-squaremessage-squaremessage-square2linkfedilinkarrow-up19arrow-down11
arrow-up18arrow-down1message-squareModel Design Theory Tips/Tricks/Docs (for a card game agent)plus-squaretaaz@biglemmowski.winEnglish · edit-21 year agomessage-square2linkfedilink
spaduf@slrpnk.netEnglish · 1 year agoTransformer-Based Large Language Models Are Not General Learners: A Universal Circuit Perspectiveplus-squareopenreview.netexternal-linkmessage-square0linkfedilinkarrow-up115arrow-down10
arrow-up115arrow-down1external-linkTransformer-Based Large Language Models Are Not General Learners: A Universal Circuit Perspectiveplus-squareopenreview.netspaduf@slrpnk.netEnglish · 1 year agomessage-square0linkfedilink
filister@lemmy.worldEnglish · 1 year agoGPU Recommendationplus-squaremessage-squaremessage-square0linkfedilinkarrow-up115arrow-down13
arrow-up112arrow-down1message-squareGPU Recommendationplus-squarefilister@lemmy.worldEnglish · 1 year agomessage-square0linkfedilink
ylai@lemmy.mlEnglish · 1 year agoUnderstanding GPU Memory 2: Finding and Removing Reference Cyclesplus-squarepytorch.orgexternal-linkmessage-square0linkfedilinkarrow-up111arrow-down11
arrow-up110arrow-down1external-linkUnderstanding GPU Memory 2: Finding and Removing Reference Cyclesplus-squarepytorch.orgylai@lemmy.mlEnglish · 1 year agomessage-square0linkfedilink
tomjuggler@lemmy.worldEnglish · 1 year agoI hired a pirate to take orders for my entertainment business - Circus Scientistplus-squarewww.circusscientist.comexternal-linkmessage-square0linkfedilinkarrow-up13arrow-down13
arrow-up10arrow-down1external-linkI hired a pirate to take orders for my entertainment business - Circus Scientistplus-squarewww.circusscientist.comtomjuggler@lemmy.worldEnglish · 1 year agomessage-square0linkfedilink
spaduf@slrpnk.netEnglish · 1 year agoTheoretical Foundations of Graph Neural Networks - Seminarplus-squarewww.youtube.comexternal-linkmessage-square0linkfedilinkarrow-up14arrow-down11
arrow-up13arrow-down1external-linkTheoretical Foundations of Graph Neural Networks - Seminarplus-squarewww.youtube.comspaduf@slrpnk.netEnglish · 1 year agomessage-square0linkfedilink
spaduf@slrpnk.netEnglish · edit-21 year agoFull MIT Lectures on Machine Learning in Genomicsplus-squarewww.youtube.comexternal-linkmessage-square0linkfedilinkarrow-up16arrow-down10
arrow-up16arrow-down1external-linkFull MIT Lectures on Machine Learning in Genomicsplus-squarewww.youtube.comspaduf@slrpnk.netEnglish · edit-21 year agomessage-square0linkfedilink
Wilshire@lemmy.worldEnglish · 2 years agoTraining AI to Play Pokemon with Reinforcement Learningplus-squareyoutu.beexternal-linkmessage-square1linkfedilinkarrow-up116arrow-down11
arrow-up115arrow-down1external-linkTraining AI to Play Pokemon with Reinforcement Learningplus-squareyoutu.beWilshire@lemmy.worldEnglish · 2 years agomessage-square1linkfedilink
LoveOxygenProducers@lemmy.worldEnglish · 2 years ago[R] Unraveling the Mysteries: Why is AdamW Often Superior to Adam+L2 in Practice?plus-squaremessage-squaremessage-square2linkfedilinkarrow-up120arrow-down11
arrow-up119arrow-down1message-square[R] Unraveling the Mysteries: Why is AdamW Often Superior to Adam+L2 in Practice?plus-squareLoveOxygenProducers@lemmy.worldEnglish · 2 years agomessage-square2linkfedilink
abhi9u@lemmy.worldEnglish · 2 years agoAn Analysis of DeepMind's 'Language Modeling Is Compression' Paperplus-squarecodeconfessions.substack.comexternal-linkmessage-square0linkfedilinkarrow-up110arrow-down11
arrow-up19arrow-down1external-linkAn Analysis of DeepMind's 'Language Modeling Is Compression' Paperplus-squarecodeconfessions.substack.comabhi9u@lemmy.worldEnglish · 2 years agomessage-square0linkfedilink
