Convolutional Neural Networks: CNN Math Explained
How do convolutional neural networks work? CNN math explained with kernels, padding, stride, pooling, receptive fields, and a full backpropagation example.
DeepSeek V4 Inside: One Token Through Every Block
How does DeepSeek V4 process one token? I follow the byte p in deepseek through CSA, HCA, mHC, MoE, and MTP on a toy width, with Flash-0731 sizes.
Looped Transformers Explained: Recurrent Depth and Astra
What is a looped transformer? How recurrent depth reuses layers, why Nanbeige 4.2 runs a 22-layer stack twice, and why that does not hide chain of thought.
DeepSeek V4 Explained: Long-Context Engineering and Math
A verification-first look at DeepSeek V4 claims, plus the real math behind sparse attention, KV-cache scaling, and long-context training stability.