Clear explanations of core machine learning concepts, from foundational ideas to advanced techniques. Understand attention mechanisms, transformers, skip connections, and more.
Deep dive into C++ memory allocation — stack frame internals, heap allocator mechanics, fragmentation, performance benchmarks, custom allocators, RAII, and debugging with AddressSanitizer and Valgrind.
18 min read · intermediate
Learn how initramfs enables Linux boot by loading essential drivers before the root filesystem mounts. Explore early userspace initialization.
15 min read
How multi-head attention runs scaled dot-product attention in parallel across several representation subspaces to build context-aware token embeddings.
7 min read · intermediate
Compare anchor-based vs anchor-free object detection: Faster R-CNN and RetinaNet anchors vs FCOS and CenterNet point-based methods.
12 min read · intermediate
Understanding complete, dimensional, and cluster collapse — the failure modes that every self-supervised method must prevent. Learn why collapse happens and how contrastive, asymmetric, regularization, and masking approaches solve it.
10 min read · advanced
How a transformer’s per-token outputs become one embedding: CLS, mean, max, last-token, and attention pooling — what each does and when to use it.
9 min read · intermediate