Subinthapa·Sep 27GRU From First Principles: The Two Gates That Make RNNs Actually WorkA short, math-first look at Gated Recurrent Units, and why they exist at allA response icon1A response icon1
Subinthapa·Sep 23LSTM From First Principles: Math, NumPy, and TensorFlowUnderstanding Long Short-Term Memory Networks From a Single Block of Equations to a Working Sentiment ClassifierA response icon1A response icon1
Subinthapa·Sep 19RNN From First Principles: Math, NumPy, and TensorFlowUnderstanding Recurrent Neural Networks From a Single Equation to a Working Sentiment ClassifierA response icon1A response icon1
Subinthapa·Sep 14From 82% to 98%: Building a Tumor Detector With a CNNA real histopathology dataset, an unstable first run, and what finally worked
Subinthapa·Sep 12SQL Server From the Ground Up: A Practical Guide to T-SQL, Joins, CTEs, and ViewsFrom CREATE TABLE to Practical Analytical Queries, Built on One Consistent Database
Subinthapa·Sep 7Building a Cat vs Dog Classifier That Works the Same Way TwiceL2 regularization, graduated dropout, augmentation, and Docker: what each one actually did, and what it didn’tA response icon1A response icon1
Subinthapa·Sep 6How Convolutional Neural Networks Actually SeeThe Complete Guide to Pixels, Kernels, Convolution, Learning, and Building a CNN From First PrinciplesA response icon2A response icon2
Subinthapa·Aug 31How Neural Networks Actually Learn: Gradient Descent, Backpropagation, the Chain Rule, and SGDA Complete Guide From First Principles to Python ImplementationA response icon2A response icon2
Subinthapa·Aug 20Regularization Explained: The Complete Guide to L1, L2, and Elastic NetWhy Models Overfit, What Regularization Actually Does, and How to Choose Between Lasso, Ridge, and Elastic NetA response icon1A response icon1
Subinthapa·Jul 24Drawing the Line: The Math Behind Support Vector MachinesHow a Simple Line, a Margin, and a Trick With Dimensions Let Machines Separate Data