Learn
Lectures on machine learning in plain language: one simple model, the math behind it, where it breaks, and what comes next.
The Single-Layer Perceptron
From the biological idea to deep learning: the model, the learning rule, the convergence theorem, the XOR problem and hidden layers, with runnable code.
read →
The Math of Linear Attention
What you need to grasp linear attention (Kimi DeltaNet): vectors and the dot product, O(n) vs O(n²) complexity, gating, recurrent state, element-wise updates.
soon