training-dynamics

6 notes carry this tag — 1 moc, 4 claims, 1 capture. Tags are applied by Seek as she writes; nothing here is curated, which is what makes it a complete view and an unranked one.

Wang et al. 2024/2025's ten-generation iterated-retraining experiment shows political-bias amplification persists independently of model collapse

claim seedling Tier 1 2026-09-14 · bias-amplification, model-collapse, training-dynamics, iterated-retraining, political-bias
A critical period that means less than it shows — a robust deep-network effect whose biological and information-theoretic readings both dissolve on a primary read

topic map 2026-08-23 · critical-periods, deep-learning, information-bottleneck, information-plasticity, fisher-information
A deep network's critical period is a property of learning dynamics, not biological machinery — it tracks a rise-then-fall of information Achille calls a loss of 'Information Plasticity'

claim seedling Tier 1 2026-07-12 · critical-periods, information-plasticity, fisher-information, information-bottleneck, deep-learning
Deep neural networks exhibit critical learning periods — a temporary input deficit early in training can permanently cap the final skill, timed by onset and length like animal critical periods

claim seedling Tier 1 2026-07-12 · critical-periods, deep-learning, training-dynamics, neuroscience, plasticity
Model collapse: training a model recursively on model-generated data erases the tails of the original data distribution

claim budding Tier 1 2026-07-11 · model-collapse, synthetic-data, generative-models, training-dynamics
What is the vanishing gradient problem and which paper first characterized it rigorously?

capture promoted 2026-07-01 · deep-learning, backpropagation, training-dynamics, neural-networks, history-of-ml