KKehinde Onasanya13h ago · 10 min readLogistic Regression in Python: Math to ImplementationLogistic regression is a supervised machine learning algorithm used for classification tasks, particularly binary classification, where the goal is to predict one of two possible classes. Unlike lineakehindeonasanya.hashnode.dev
NNguyễn Hữu ĐứcJul 11 · 3 min readBuilding an LLM System from Scratch in Pure Python & NumPy: Architecture, Invariants, and Clean Code, Open-Source 100% Inference Engine and Thinking engine!Hi everyone, I wanted to share the design invariants and architecture of Draco AI, a full-stack, hardware-agnostic LLM system built completely from scratch in pure Python and NumPy. The core philosophdraco-ai.hashnode.dev
PPrasanth MadhurapantulaJun 16 · 7 min readBuild your own Redis from scratch, and talk to it with the real redis-cliRedis has a reputation for being a serious piece of infrastructure, and it is. But the core of it, the part that makes it Redis, is astonishingly small. Small enough that you can rebuild it in about 81iwtlp.hashnode.dev
PPrasanth MadhurapantulaJun 15 · 10 min readBuild your own git from scratch, and watch its hashes match the real thingAlmost everyone uses git every day and almost no one knows what it does. We learn the verbs, add, commit, push, pull, and treat the rest as a black box that occasionally eats our work. But the core of1iwtlp.hashnode.dev
PPrasanth MadhurapantulaJun 10 · 3 min readMachine learning from scratch, what to build before using scikit-learnmodel.fit(X, y) is one line, and that is the problem. scikit-learn is excellent, but reaching for it before you understand what it does leaves you able to call models without being able to reason abou1iwtlp.hashnode.dev
AAarthy VarathanApr 17 · 5 min readDeep Learning from scratch - (1)What if you could build a neural network using nothing but Python and a bit of math, no libraries, no magic, no black boxes? Today, most people learn deep learning using powerful frameworks like Tensoaarthy.hashnode.dev
SSai CharanApr 13 · 42 min readLogistic Regression Is Not a Classifier: From Bernoulli Likelihood to Hessian Convexity, Newton's Method, and the Failures Nobody Talks AboutThis post builds it from the ground up. From the Bernoulli distribution to the Hessian proof to Newton's method to the exact moment the math collapses — no black boxes, no skipped steps. The Hook Not 1saicharan8855.hashnode.dev
AArbash HussainMar 23 · 12 min readUnderstanding the Perceptron: Intuition, Theory, and CodeIntroduction Deep learning drives many technologies we use daily, such as recommendation systems, speech recognition, and computer vision. Before neural networks evolved into their current complexity,1cckeh.hashnode.dev
Eezedin ahmedDec 12, 2025 · 1 min readbuilding Http server from scratchbuilding http server using javaezedincode.hashnode.dev
JJefferson FerreiraOct 17, 2025 · 3 min readO Byte Fantasma: Por que minha struct era maior que a soma de suas partes?Na minha saga de construir um SGBD educacional para meu TCC, a primeira regra é: o tempo é curto. Bastante curto. Com o relógio correndo, precisei definir um escopo brutalmente focado: o Gerenciador de Armazenamento. Por que começar por ele? Porque e...jefferson-f.hashnode.dev