The basic motivation is that vocabularies are unbounded, but embedding tables can only be a fixed size. If you know your training data matches up to your test data well, this isn't such a big deal for most applications. If it's rare at training time, it'll be rare at test time.
AI
-
Netscape to Internet as ChatGPT to Artificial Intelligence
By
–
Netscape was to the Internet what ChatGPT is to Artificial Intelligence. h/t @dharmesh
-
Company Leadership Blamed for Poor Strategic Decisions Affecting Staff
By
–
This looks like company leadership trying to pass the blame to employees for their own bad decisions https://
x.com/TheRudinGroup/
/TheRudinGroup/status/1604884877572067333
… -
Apple Store App Toggle Feature Differences Explained
By
–
Oh indeed there is a toggle on the Apple Store app and the App Store app. Others don’t have one.
-
ChatGPT: Millions of Linguists Working on Language Model
By
–
Imagine millions of linguists working for decades on an extremely complex model of language based on all the text ever written. That’s essentially what ChatGPT is.
-
AI-Based Fitness Trainer Application for Squat Analysis
By
–
Today we will build an AI-based Fitness Trainer application that analyzes squats and provides appropriate feedbackhttps://t.co/6987UxxwwK#fitnesstrainer #squatanalyzer #squat #artificialintelligence #computervision #deeplearning #ai #machinelearning #poseestimation #mediapipe pic.twitter.com/64cWBTP5Rx
— Satya Mallick (@LearnOpenCV) 20 décembre 2022Today we will build an AI-based Fitness Trainer application that analyzes squats and provides appropriate feedback https://
learnopencv.com/ai-fitness-tra
iner-using-mediapipe/
… #fitnesstrainer #squatanalyzer #squat #artificialintelligence #computervision #deeplearning #ai #machinelearning #poseestimation #mediapipe -
Annotation Quality Comparison and ML Impact on Professional Fields
By
–
Does the paper also compare the quality of the annotations? Re: Tsunami. There was a recent thread about how the market for translation was destroyed by ML. It will happen one field at a time… so the impact is incremental.
-
Petals Creates Free Distributed Network for Running Text-Generating AI
By
–
Cool article from @Kyle_L_Wiggers @TechCrunch about Petals by @BigscienceW https://
techcrunch.com/2022/12/20/pet
als-is-creating-a-free-distributed-network-for-running-text-generating-ai
…