「#クロスエントロピー損失」の人気タグ記事一覧｜note ――つくる、つながる、とどける。

ALPINE: Unveiling the Planning Capability of Autoregressive Learning in Language Models

6か月前

Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory

6か月前

Understanding Emergent Abilities of Language Models from the Loss Perspective

7か月前

Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels

7か月前