WORK
Projects, research, and notes — filter by kind to narrow the list.
The CIFAR-10 architecture of §4.2 rebuilt from the paper's description, checked against Table 6, and run twenty-two times to find which parts of the degradation claim survive reseeding.
Six configurations rebuilt from Table 1, four of the paper's prose claims measured, and Table 5's protocols reproduced on all 50,000 ILSVRC-2012 validation images.
The 2012 architecture reproduced to the paper rather than to torchvision — the two-GPU grouped convolutions, LRN before pooling, and the bias initialisation that most implementations drop. Verified at exactly 60,965,224 parameters, with 33 questions the paper raised and how each one resolved.
The 1998 architecture reproduced faithfully in PyTorch — trainable subsampling coefficients, the C3 connection table, RBF output and MAP loss — verified at exactly 60,000 parameters. With 21 questions the paper raised and how each one resolved.
