Here is a great resource to understand how Gradient Descent works and learn about many of its variations: https://
ruder.io/optimizing-gra
dient-descent/
… via @seb_ruder And it's completely FREE.
MACHINE LEARNING
-

Free Resource on Gradient Descent Optimization Techniques and Variations
By
–
-

Zero-shot AI accelerates drug discovery and antibody design
By
–
Please enjoy my interview with Absci CEO Sean McClain Absci: Will ‘zero-shot’ AI change drug discovery? “We can get everything right the first time and dramatically reduce the time it takes to get into the clinic.” https://
thetechnologyletter.com/the-posts/absc
i-ceo-mcclain-we-will-be-the-first-company-to-put-an-antibody-designed-by-computer-into-a-human
… // $ABSI -

ChatGPT: Everything You Really Need To Know Simply
By
–
ChatGPT: Everything You Really Need To Know (In Simple Terms) https://
forbes.com/sites/bernardm
arr/2022/12/21/chatgpt-everything-you-really-need-to-know-in-simple-terms/
… #AI #MachineLearning #DataScience #IoT #100DaysofCode #womenwhocode #serverless #Robots @FmFrancoise @CatherineAdenle @Shi4Tech @enilev #BigData #Analytics #DeepLearning #DigitalTransformation -
Optimizing AI Value: Measurement and Research Insights
By
–
Optimize & Measure #AI value! Join Lars Lind Principal @adlittle @EHedfors VP @EricssonDigital & I http://
bit.ly/AIValueImpact + New #research here! http://
bit.ly/3Fr53mQ #ML #tech #EricssonAmbassador @ipfconline1 @DeepLearn007 #100DaysOfCode @ahier @andy_fitze @jblefevre60 -
Extending arithmetic findings to unseen pre-training tasks
By
–
Cool work! In addition to arithmetic, I wonder how much these findings apply to a task that is not seen much in pre-training, such as last letter concatenation or coin flip
-
Dreambooth vs Large-Scale Training: AI Model Fine-Tuning Techniques
By
–
So dreambooth is usually 10-20 pics of one person. This is thousands of random pics to improve it. Both similar technique but slightly different approach
-

Training Custom Stable Diffusion Model with Personal Dataset
By
–
Pics of my first FULLY self trained Stable Diffusion (not Dreambooth) with my own data set These are just samples as it's not even fully done training Will train on men next! Then a combo model
-

Learning Python Notebooks GPU Training Model Development
By
–
Today I learnt how Python notebooks work and how to run them on a GPU and train my own model better
-
Project Relate: Machine Learning Speech Recognition for Non-Standard Speakers
By
–
Following years of research featuring thousands of people who recorded over a million speech samples, we released Project Relate in beta. This Android app uses machine learning to offer personalized speech recognition for non-standard speakers. https://
g.co/projectrelate