#VEX
45 related articles
·4 min
Statistical Foundations of Machine Learning: From MLE to EWMA and Deep Learning Optimizer Principles
Deep dive into core ML statistics: MLE derivations, multivariate Gaussian, linear regression and least squares equivalence, empirical risk minimization, method of moments, and how EWMA connects to Adam optimizer.
Read more →
·4 min
Statistical Foundations of Machine Learning: From MLE to EWMA and Deep Learning Optimizer Principles
Deep analysis of core ML statistics concepts covering MLE derivation, multivariate Gaussian, linear regression and least squares equivalence, empirical risk minimization, method of moments, and EWMA's connection to Adam optimizer.
Read more →
·4 min
Opus 5 Real-World Testing: Cheaper Yet Stronger — Why It's Now My Default Coding Model
In-depth testing of Claude Opus 5's coding abilities vs Fable 5 and 5.6 Sol. Why Opus 5 outperforms pricier models at half the token cost, plus selection guide and distillation explained.
Read more →
·4 min
15-Year-Old DIY Maker Builds High-Torque Precision Joint: $200 vs. $2000 Industrial-Grade
A 15-year-old maker builds a robotic arm shoulder joint for $200 using timing belts, cycloidal drive, and capstan drive with 480:1 total reduction, challenging $2000 industrial joints.
Read more →
·4 min
15-Year-Old DIY Maker Builds High-Torque Precision Joint: $200 vs. $2,000 Industrial-Grade
A 15-year-old maker built a $200 robotic arm shoulder joint using a multi-stage reduction drivetrain (timing belt + cycloidal drive + capstan drive) with a 480:1 ratio, challenging $2,000 industrial joints.
Read more →
·4 min
OpenAI Merges Codex and ChatGPT: Deep Dive into Three New Models + Agent Workflows
OpenAI merges Codex and ChatGPT into a unified platform while launching three new models: SOUL, TERRA, and LUNA. Deep dive into Computer Use, loop workflows, multi-threading, and the Agent Native strategy.
Read more →
·2 min
How to Choose a Programming Language? A Rational Look at the Truth Behind Language Selection
Java, Python, Go, or a niche language? This article rationally analyzes programming language selection across three dimensions — probability, difficulty, and growth potential — to help you escape language-choice anxiety.
Read more →
From Math to AI Research Engineer: A D…
·2 min
From Math to AI Research Engineer: A Deep Dive into the Viral GitHub Learning Roadmap
A GitHub project called maths-cs-ai-compendium surpassed 6,000 Stars with a roadmap for becoming an AI/ML Research Engineer. Here's what makes it worth following.
Read more →
·3 min
How to Choose AI Learning Books: A 5-Dimension Rational Evaluation Framework
How to evaluate AI/ML books rationally? Use these 5 dimensions—content depth, code quality, currency, community reputation, and companion resources—to choose wisely.
Read more →
·3 min
OpenAI Merges ChatGPT and Codex: The Birth of an AI OS and Four Core Strategies
OpenAI merges ChatGPT and Codex into a Super App, unveiling the early blueprint of an AI OS. A deep-dive into four core strategies: Loop workflows, tool stack economy, multi-threading, and Sites.
Read more →
·3 min
AI/ML Students Lost in Job Search? A Deep Comparison of Four Career Paths and How to Choose
AI/ML students unsure which career path to pursue? Compare AI engineering, SDE, PM, and UI/UX in depth — with honest entry barriers and a practical self-assessment framework.
Read more →
·2 min
Symbolic AI and Neural Networks: A Systematic Learning Path and Core Mathematical Tools
A deep dive into symbolic vs. neural AI paradigms — exploring type theory, category theory, and algebraic geometry as mathematical bridges toward neuro-symbolic integration.
Read more →
·3 min
Convergence Analysis of High-Order ODE Solvers for Diffusion Models: Error Bounds and Fast Sampling Theory
A deep dive into convergence theory for high-order ODE solvers in diffusion models: error decomposition, Ghost Flow construction, C2 regularity verification, and the mathematical foundations of DPM-Solver fast sampling.
Read more →
decisionrl: An Open-Source Reinforceme…
·2 min
decisionrl: An Open-Source Reinforcement Learning Library Built for Operational Decision-Making
decisionrl is an open-source RL library for operational decisions, with built-in environments for inventory, pricing, supply chain, and OR baselines for comparison. Built on PyTorch, MIT licensed.
Read more →
·6 min
OpenAI Merges ChatGPT and Codex: The Super App for the AI Agent Era Is Here
OpenAI merges ChatGPT and Codex into a super app and releases three new GPT-5.6 models: Sol, Terra, and Luna. A deep dive into four hands-on workflows—Computer Use, Loops, and multi-threading—for the AI agent era.
Read more →
·3 min
Math Foundations for Machine Learning: A Roadmap Covering Four Core Areas with Recommended Resources
Struggling with math for ML? This guide covers linear algebra, calculus, probability, and optimization with top resources like 3Blue1Brown and Mathematics for Machine Learning.
Read more →
Using Claude for Constrained Optimizat…
·2 min
Using Claude for Constrained Optimization Research: The Promise and Limits of AI-Automated Science
How Claude and LLMs assist constrained optimization research — from problem modeling to solver integration. An honest look at AI's real capabilities and limits in automated science.
Read more →
The Theory of Deep Learning: Why Do Ne…
·4 min
The Theory of Deep Learning: Why Do Neural Networks Work? A Complete Overview of Theoretical Research
Deep learning shines in practice, but why does theory always lag behind? This article surveys the over-parameterization paradox, implicit regularization, NTK, the information bottleneck, and more.
Read more →
·5 min
The Real Bottleneck in Materials Innovation: Why Scaling Up Is Harder Than Discovery
Why do lab breakthroughs in materials struggle to reach the market? An in-depth analysis of the core bottleneck from discovery to mass production—covering physical process challenges, economic thresholds, academic incentive imbalances, and paths forward in the AI era.
Read more →
·3 min
K-means vs Random Forest: How to Choose the Right Algorithm from First Principles
A machine learning exam question pitting K-means against Random Forest sparks debate. Learn the core difference between supervised and unsupervised learning, and how to choose the right algorithm for mixed-feature tasks.
Read more →