Speech-to-text can't tell you if an AI voice said a name rightWe make short, AI-voiced lessons. Before a video ships, every sentence goes through automatic checks, and then a person listens. The automatic checks kept failing in one place: names. This post explai5 min read·logitsolutionsai.hashnode.dev23D10h ago
Batch normalization, visually: the reset that keeps deep networks steadyDeep Learning, Visually #20 Watch the Short: youtube.com/shorts/yYxpjlvW69s Why the numbers drift A deep network is a chain of layers. Each layer takes a weighted sum of the activations from the layer5 min read·logitsolutionsai.hashnode.dev1d ago
Why did deep networks stop learning?Vanishing and exploding gradients: why blame fades or blows up on its way back through a deep network, and the fixes that made deep learning work5 min read·logitsolutionsai.hashnode.dev6d ago
Why does every AI start out random?Weight initialization: why a network's dials must start different, and how big the random start should be6 min read·logitsolutionsai.hashnode.dev6d ago
Why slow down near the finish line?Learning-rate schedules: start big, halve the step size every so often, and settle where one step size can't6 min read·logitsolutionsai.hashnode.devNov 1