Rahultiwari·Nov 4PCA Explained Visually: How Machine Learning Compresses Many Features Without Losing the Bigger…There is a point in almost every machine learning project where adding more features stops feeling helpful.
Arif Akbarul Huda·Oct 20Finding a Racket in a Wrist SensorI play badminton once a week, without a coach. In two years I have not improved. I did not know the techniques, and I naively thought all…
Navyasri Kothuri·Oct 18Beyond the Black Box #7 — Support Vector Machines (SVM): How Can a Machine Find the Best Boundary?A beginner-friendly look at maximum margins, support vectors, kernels, and how SVM classifies data.
Azalihassan·Oct 11Can a Straight Line Detect a Power-Line Fault? Logistic Regression vs. SVMA practical comparison of feature engineering and machine-learning classifiers for three-phase transmission-line fault detection.
InData Science CollectivebyAbhisake Jain·Oct 9Only 3 of 60 Points Matter: The Simple Idea Behind Support Vector MachinesMost of your data does not matter. A few special points decide everything. Here is how to find them.A response icon1A response icon1
InData Science CollectivebyAbhisake Jain·Sep 26The Kernel Trick: How Machine Learning Turns an Impossible Curve Into a Straight Line.Some problems can’t be solved where they start. So machine learning quietly moves them somewhere easier.A response icon1A response icon1
Jasminesardana·Sep 9Logistic Regression vs Linear SVM for Text Classification: What I Learned From a Real NLP ProjectComparing two classical ML models on a real customer support ticket classification problem — before moving on to DistilBERT.A response icon1A response icon1
Gülşah Demiryürek·Sep 1Storage Virtual Machine (SVM) ve Veri ProtokolleriStorage Virtual Machine (SVM) ve Veri Protokolleri
badarinath·Jul 26SVM Isn’t As Scary As Your Textbook Makes It SoundWhen I first learnt SVM, every explanation started with hyperplanes. That was exactly why I never understood it. Nobody tells you what…
