Machine Learning
1297 Threads
Over the past few weekends, I've experimented with using LLMs to build a simple assistant. Here's a write-up of what I built, how I built them, and their potential. Also, some sho...
In recent days, I shared various resources on finetuning large language models. Multiple people reached out asking what I think about in-context learning. 1/6 https://t.co/w0ayXPp...
Wanna learn how to develop and **deploy** a cutting-edge NLP product, using โ only Python ๐, and โ managing 0 infrastructure ๐ Here is an ML product you can develop and ship tod...
If you want to learn how to train bigger LLMs (I realize that's a pleonasm ๐ , meaning roughly 1B+ params models) here is a couple of amazing resources: 1) This one by @borisdayma...
Training an ML model inside a Jupyter notebook is something every data scientist knows ๐๏ธ But do you know how to create a real-world ML service that makes a difference for the com...
In machine learning, we take gradient descent for granted. We rarely question why it works. What's usually told is the mountain-climbing analogue: to find the valley, step towards...
Don't pay ridiculous amount of money to learn Data Science & Machine Learning. The likes of MIT, Stanford, DeepMind & Cornell Tech are offering comprehensive courses in Machine Le...
K-Means has two major problems: - Number of clusters must be known - Doesn't handle outliers But there's a solution! Introducing DBSCAN, a Density based clustering algorithm. ๐...
AI prompting is the next biggest skill to learn. Companies are now paying up to $335,000/year for Prompt Engineers. Here are the most Advanced ChatGPT prompting techniques that m...
Wanna build a Machine Learning app that solves a real-world business problem? Here are the 6 steps to get there โโโ
Big News! Meta just released Segment Anything, a new AI model that can "cut out" any object, in any image/video, with a single click. The model is designed and trained to be promp...
Matplotlib polar-plots clearly explained! ๐ Today, we learn about: - Polar Scatter Plot - Radar Plot - Pie-Chart - Polar Bar Chart A Thread ๐งต๐ https://t.co/ZvFZg6ISkI
@yy_hezhi @dwhitena @predictionguard @LangChainAI @SaveToNotion @threadreaderapp @readwise @pdfmakerapp Saved! Here's the compiled thread: https://t.co/WHhrxnVrxj ๐ช AI-generated s...
@nihilistPengu @arimorcos @SuryaGanguli @sshkhr16 @MetaAI Saved! Here's the compiled thread: https://t.co/ibdjlffbfZ ๐ช AI-generated summary: "We show that exponential scaling is...
ChatGPT Hyperparameter Tips ๐ WARNING: ADVANCED TUTORIAL โ ๏ธ Hyperparameters are adjustable settings that determine the behavior of the language model during training and inferenc...
๐ Series: Simplifying Top 10 ML Algorithms Topic 6: Everything About K-Nearest Neighbor (KNN) Algorithm for Machine Learning Beginners ๐ง๐ผโ๐ป 1/12 ๐งต๐ https://t.co/a8qfxF1pCx
The neural architecture of GPT is v.different from Homo; We just have a lesser idea of what is going on inside the black box when it extracts a degree of logic from a LLM; yet intu...
Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm https://t.co/qHofPPjZaY Using GPT-3 as a case study, we show that 0-shot prompts can significantly outp...
YouTube channels for Data Science: โฏ Mathematics โ 3Blue1Brown โฏ Python โ Corey Schafer โฏ SQL โ Joey Blue โฏ MS Excel โ ExcelIsFun โฏ Tableau โ Tableau Tim โฏ PowerBI โ Guy in a Cube...
You have a model, that is perfect, but after a while, it starts to perform badly? Model performance decay is a real issue. But what causes it? I will explain in this thread. 1/...
95% of Machine Learning in the industry uses tabular data, yet most people can't stop talking about ChatGPT. Let's do something different: Let's build a simple tabular model toge...
Stanford University is offering free online courses. No application or fee required. Here are 5 FREE courses you don't want to miss in 2023:
I am very excited to announce I have been successful in installing and operating a full ChatGPT knowledge set and interface fully trained on my local computer and it needs no Inter...
Machine Learning models are sneaky little bastards that use any available shortcuts to optimize their evaluation metric. Every tutorial speaks about splitting your data randomly....