We've done ddpm from scratch in the latest course. Lemme know if you want more info
MACHINE LEARNING
-
AI Requires Right Data Quality Machine Learning Success
By
–
Artificial Intelligence Without The Right Data Is Just… Artificial https://
forbes.com/sites/joemcken
drick/2022/12/30/artificial-intelligence-without-the-right-data-is-just-artificial/
… @joemckendrick #AI #MachineLearning #DataScience #IoT #100DaysofCode #womenwhocode #serverless @anijov @FmFrancoise @CatherineAdenle @Shi4Tech @enilev #BigData #Analytics #DeepLearning -
Dropout Improves Model Performance to 95.2% Accuracy
By
–
After adding dropout, I increased the 5 epoch best to 93.2%, and christopherthomas on http://
forums.fast.ai improved the 50 epoch best to 95.2% – first time we've gotten a result >95%! 😀 -
ML Development: Prioritize Quality-of-Life Code Improvements
By
–
When editing an ML codebase, I recommend constantly taking small detours to make quality-of-life tweaks as you notice them, rather than send them off to languish in a bug tracker. Highest order bit in ML in iteration speed, and these small pains add up faster than you know.
-
NeurIPS 2023 Program Chair Nomination Open Call
By
–
You can nominate yourself as Program Chair for #NeurIPS2023. Who is up for the challenge? https://
x.com/NeurIPSConf/st
/NeurIPSConf/status/1607783374843781121
… -
Limitations of Generative AI Tuning and Data Distribution
By
–
Being able to produce outputs for an arbitrary input doesn’t give you the ability to reproduce the input distribution of the tuning data. Even if you somehow can, tuning on the generations of a tuned model is like making a copy of a copy of a VHS tape.
-
Transformers and LSTMs: Scaling architectures and the need for innovation
By
–
I agree with the core thing I think you’re saying: there’s lots of architectures that could allow models to scale with respect to both data and computation. Transformers are one, maybe not even a good one. But LSTMs as we have then don’t scale — so we were missing an invention
-
Top 5 AI Podcast Episodes 2022: ML Trends Explored
By
–
Our AI Podcast has attracted more than 3.6M listens to date from folks who want to hear the latest in machine learning. Check out the top 5 episodes of 2022 on topics like game development, autonomous vehicles and more.
-
Free Machine Learning Courses from Top Universities
By
–
100% FREE machine learning courses from top Colleges: – MIT 6.S191 Introduction to Deep Learning
– DS-GA 1008 Deep Learning
– UC Berkeley Full Stack Deep Learning
– UC Berkeley CS 182 Deep Learning
– Cornell Tech CS 5787 Applied Machine Learning -
Fine-tuning AI Models: Adjusting Weights and Prompting Techniques
By
–
Adjusting the weights of an existing model, not training from scratch. When you fine-tune (with enough examples), you don’t include instructions in the prompt. See OpenAI’s fine-tuning guide here: https://
beta.openai.com/docs/guides/fi
ne-tuning
…