Filter
Exclude
Time range
-
Near
๐ŸŽž๏ธืฉื•ืžืขื™ื ืžื™ืœื™ื ื›ืžื• ื”ืกื™ืืŸ ื•ื’ืจื“ื™ืื ื˜ ื•ื ื‘ื”ืœื™ื? ืžื™ื™ืง ื™ืขืฉื” ืœื›ื ืงืฆืช ืกื“ืจ ื‘ื‘ืœื’ืŸ. ๐Ÿฆื‘ืœืžื™ื“ื” ืขืžื•ืงื” ืื ื—ื ื• ื–ื•ืจืงื™ื ืืช ื”ืžื•ืฉื’ "ื’ืจื“ื™ืื ื˜" ืœืื•ื•ื™ืจ ื›ืœ ื”ื–ืžืŸ, ืื‘ืœ ื›ื“ื™ ืœื”ื‘ื™ืŸ ื‘ืืžืช ืžื” ืงื•ืจื” ืžืื—ื•ืจื™ ื”ืงืœืขื™ื ืฉืœ ืžื ื•ืขื™ ื—ื™ืฉื•ื‘ ื›ืžื• PyTorch, ื—ื™ื™ื‘ื™ื ืœื”ื›ื™ืจ ืืช "ื”ืฉื™ืœื•ืฉ ื”ืงื“ื•ืฉ" ืฉืœ ื”ื—ืฉื‘ื•ืŸ ื”ื“ื™ืคืจื ืฆื™ืืœื™. ๐Ÿ”น ื’ืจื“ื™ืื ื˜ : ื”ืžืฆืคืŸ ื”ื•ื ืœื•ืงื— ืคื•ื ืงืฆื™ื” ืฉืžื—ื–ื™ืจื” ืกืงืœืจ (ืคื•ื ืงืฆื™ื™ืช ื”-Loss ืฉืœื ื•) ื•ื’ื•ื–ืจ ืื•ืชื” ืœืคื™ ื›ืœ ื”ืžืฉืงื•ืœื•ืช. ื‘-Gradient Descent ืื ื—ื ื• ื”ื•ืœื›ื™ื ื ื’ื“ ื”ื›ื™ื•ื•ืŸ ืฉืœื• ื›ื“ื™ ืœืžื–ืขืจ ืืช ื”ืฉื’ื™ืื”. ื”ื•ื ื”ืฉื•ืจื” ื”ืชื—ืชื•ื ื” ืฉืœ ืชื”ืœื™ืš ื”ืœืžื™ื“ื”. ๐Ÿ”น ื™ืขืงื•ื‘ื™ืืŸ: ืžื ื•ืข ื”-Backprop ืจืฉืช ื ื•ื™ืจื•ื ื™ื ืขืžื•ืงื” ื”ื™ื ื‘ืขืฆื ืฉืจืฉืจืช ืฉืœ ืคื•ื ืงืฆื™ื•ืช ืฉืžืงื‘ืœื•ืช ื•ืงื˜ื•ืจื™ื ื•ืžื—ื–ื™ืจื•ืช ื•ืงื˜ื•ืจื™ื (ืชื—ืฉื‘ื• ืขืœ ืฉื›ื‘ื•ืช ื ืกืชืจื•ืช). ื”ื™ืขืงื•ื‘ื™ืืŸ ืžื™ื™ืฆื’ ืืช ื”ื ื’ื–ืจื•ืช ืฉืœ ืคื•ื ืงืฆื™ื•ืช ื•ืงื˜ื•ืจื™ื•ืช ืืœื•. ื‘ืคื•ืขืœ, ื”ืืœื’ื•ืจื™ืชื ืฉืœ Backpropagation ืœื ืžื—ืฉื‘ ืืช ื›ืœ ืžื˜ืจื™ืฆืช ื”ื™ืขืงื•ื‘ื™ืืŸ (ืžื” ืฉื”ื™ื” ืžืคื•ืฆืฅ ืืช ื”ื–ื™ื›ืจื•ืŸ), ืืœื ืžืฉืชืžืฉ ื‘ื˜ืจื™ืง ืฉื ืงืจื VJP (Vector-Jacobian Product) ื›ื“ื™ ืœื”ืขื‘ื™ืจ ืืช ื”ืฉื’ื™ืื” ืื—ื•ืจื” ื‘ื™ืขื™ืœื•ืช. ๐Ÿ”น ื”ืกื™ืืŸ : ืžืคืช ื”ืขืงืžื•ืžื™ื•ืช ืžื˜ืจื™ืฆืช ื”ื ื’ื–ืจื•ืช ื”ืฉื ื™ื•ืช. ื”ื™ื ืœื ืจืง ืื•ืžืจืช ืœื ื• ืœืืŸ ืœืจื“ืช, ืืœื ืื™ืš ื”ืฉื™ืคื•ืข ื”ื•ืœืš ืœื”ืฉืชื ื•ืช. ื‘ืขื•ืœื ืื™ื“ื™ืืœื™, ื”ื™ื™ื ื• ืžืฉืชืžืฉื™ื ื‘ื• ืœืื•ืคื˜ื™ืžื™ื–ืฆื™ื” ืžืกื“ืจ ืฉื ื™ (ื›ืžื• ืฉื™ื˜ืช ื ื™ื•ื˜ื•ืŸ) ื›ื“ื™ ืœื”ืชื›ื ืก ืœืžื™ื ื™ืžื•ื ื‘ื”ืจื‘ื” ืคื—ื•ืช ืฆืขื“ื™ื. ื”ื‘ืขื™ื”? ืžื•ื“ืœ ืฉืคื” ืขื ืžื™ืœื™ืืจื“ ืคืจืžื˜ืจื™ื ื™ื“ืจื•ืฉ ืžื˜ืจื™ืฆืช ื”ืกื™ืืŸ ื‘ื’ื•ื“ืœ ืžื™ืœื™ืืจื“ ืขืœ ืžื™ืœื™ืืจื“. ื–ื” ื‘ืœืชื™ ืืคืฉืจื™ ื—ื™ืฉื•ื‘ื™ืช, ื•ืœื›ืŸ ืื ื—ื ื• ืžืกืชืžื›ื™ื ืขืœ ืืœื’ื•ืจื™ืชืžื™ื ืžืกื“ืจ ืจืืฉื•ืŸ (ื›ืžื• Adam) ืฉืžื ืกื™ื ืœืงืจื‘ ืืช ื”ื”ืชื ื”ื’ื•ืช ื”ื–ื•. ืœืฉืžื•ืจ ื‘ืžื•ืขื“ืคื™ื. ๐Ÿ“Œ credit 4the image: @techNmak #DeepLearning #MachineLearning #AI #MathForML
2
8
1,254
Backpropagation is the core learning mechanism behind neural networks In this video, we break down how loss is computed by measuring the error between predicted output and the actual target using Mean Squared Error (MSE). Youโ€™ll see how predictions flow through the network, how error is calculated, and why minimizing this loss is essential for training deep learning models. A must-watch if youโ€™re building strong fundamentals in Machine Learning and AI #Backpropagation #ComputeLoss #MeanSquaredError #MSE #NeuralNetworks #DeepLearning #MachineLearning #AI #DataScience #MLBasics #AIFundamentals #ArtificialIntelligence #LearningAI #MathForML #Engineering #CS #TechEducation #StudyML
2
5
893
๐Ÿ“˜ Grab the free โ€œMathematics for Machine Learningโ€ book and strengthen your ML foundations in linear algebra, calculus, probability, and optimization. Download: mml-book.github.io/book/mml-โ€ฆ #MachineLearning #MathForML #AI #DataScience #MLBook
3
122
Understanding symmetric matrices and positive definiteness is key to mastering #MachineLearning. They explain why algorithms like gradient descent actually converge! ๐ŸŽฅ Watch here โ†’ youtu.be/CgdJqxn0dlA #MathForML #AI #DeepLearning #LinearAlgebra
2
39
27 Sep 2025
Day 26 of #MathForML Today's labwork: Applications of EigenValues & EigenVectors -> Navigating Webpages -> PCA on cat images Before diving into calculus, I want to make sure my Linear Algebra is rock solid. Can you suggest resources to master and practice Linear Algebra for ML?
6
167
6 Aug 2025
Just found @geogebra โ€” one of the best tools Iโ€™ve seen for understanding math visually. Super helpful for grasping ML topics like vectors, functions, and calculus. ๐Ÿ”— geogebra.org Definitely worth checking out! #MathForML #GeoGebra #LearnInPublic
3
71
๐Ÿง  Day 68 of Diving into AI/ML Today I deepened my understanding of linear algebra concepts that power ML models. 1๏ธโƒฃ Dot Product โ€“ Measures alignment between vectors. Positive = same direction, zero = perpendicular, negative = opposite. Think of it as a projection. 2๏ธโƒฃ Cross Product (3D) โ€“ Returns a vector โฌ†๏ธ perpendicular to both inputs. Magnitude = area of the parallelogram they span. 3๏ธโƒฃ Matrix Inverse - If A transforms a vector, Aโปยน brings it back. Only works if A is square & full-rank. ๐Ÿ” 4๏ธโƒฃ Linear Transformation โ€“ Stretch, rotate, flip, or squash vectors via matrices. Always sends origin to origin, preserves lines. ๐Ÿ”„ 5๏ธโƒฃ Duality โ€“ Vectors not just as directions, but as functions measuring other vectors. #100DaysOfML #LinearAlgebra #AI #DeepLearning #MathForML #NeuralNetworks #Python
1
3
68
Day 54 #MyDataScienceJourney: Covered equations of lines, 3D planes, and hyperplanes, plus how to find a pointโ€™s distance from a plane. Also explored instance-based vs. model-based learning in MLโ€”fascinating to see how model either memorize or generalize!#LearnInPublic #MathForML
2
48
"Did some solid descriptive stats past 2 days โ€” now jumping into probability distribution functions as part of my ML grind. Letโ€™s gooo! ๐Ÿ“Šโžก๏ธ๐Ÿ“ˆ๐Ÿ”ฅ #MachineLearning #StatsJourney #AI #deeplearning #datascience #MathForML #learning #progress #AIForEveryone
1
6
120
Always been scared of math, but itโ€™s time to change that. Iโ€™m diving into linear algebra, calculus, and probability all for the love of machine learning. One step at a time. Letโ€™s do this! #MachineLearning #MathForML #AIJourney #LinearAlgebra #Calculus #Probability #KeepLearning
3
118
13 Feb 2024
Essential Math for Machine Learning: Kernel Density Estimationโžก๏ธmedium.com/@weidagang/essentโ€ฆ #AIforBeginners #DataAnalysis #MathForML #artmac #artmacllc
2
36
30 Aug 2023
Day 77 #100DaysOfCode ๐Ÿ“Š Mastered Linux basics! ๐Ÿ’ป โœ… Solved 10 Math problems for ML ( Hermitian mat & diagonalization )๐Ÿค– ๐Ÿš€๐ŸŒŸ #Linux #MathForML #100daysofcodechallenge #100daysofcoding #Ubuntu #script #Shell #SSH #VM
2
222
If you are thinking about learning maths for data science. Here are 5 great books and resources to get you started ๐Ÿ‘‡๐Ÿป #DataScience #DataAnalytics #mathforML #mathematics
2
1
841
I'm taking the Math for ML specialization from @DeepLearningAI_ which includes Linear Algebra, Calculus, and Statistics. I was always a little intimidated by calculus in ML so I hope this helps me with that. #MachineLearning #MathForML
1
3
130
Replying to @geeko77
Saved this Tweet to your Notion database. Tags: [Mathforml]
4
Exciting news for anyone looking to strengthen their math foundation for machine learning and data science - the new course Math for Machine Learning and Data Science is now available on Coursera, taught by the brilliant @luis_likes_math #MachineLearning #DataScience #MathForML
25 Jan 2023
1/Math for Machine Learning and Data Science is now available on Coursera! Taught by @luis_likes_math, this gives an intuitive understanding of the most important math concepts for AI. coursera.org/specializationsโ€ฆ
1
3
757
Replying to @julliansantosa
This thread is saved to your Notion database. Tags: [Mathforml]
3 Apr 2021
๐‘“โˆ˜๐‘”, you must have come across this in some Machine Learning course or a paper and wondered what it is! In this thread we will introduce you to some common math notations seen in ML. A thread ๐Ÿ‘‡ #mathematics #MathforML #DeepLearning
1
28
80
Feeling a bit stupid for writing code to count lines of text, when I could have just looked at the side of the editor... ๐Ÿคฆโ€โ™‚๏ธ๐Ÿ˜‚ __________ #javascript #Developer #mathforml
3
Overview of data distributions disq.us/t/3pg0vra . Probability distributions- always find them a challenging topic. Wish I had this before. #Stats #Probability #MathforML
2