http://blog.caveduck.io/tags/nvidia/Recent content in NVIDIA on Warpspace BlogHugo -- 0.154.5en-USMon, 27 Apr 2026 00:00:00 +0000http://blog.caveduck.io/posts/neural-net-pruning/Mon, 27 Apr 2026 00:00:00 +0000http://blog.caveduck.io/posts/neural-net-pruning/Starting from LeCun’s 1989 Optimal Brain Damage, this is the story of shrinking a model by cutting weights away (pruning). What to cut, how, and how much; the surprise of compression that survives even a 95% cut thanks to retraining; and the point that you only get a real payoff when the hardware (NVIDIA 2:4) backs you up — all with plots we measured ourselves on an MNIST MLP.