超级会员免费看
本文探讨了人工智能模型的真正关键是数据集，而非架构、超参数或优化器。作者通过自己的经验指出，无论模型如何调整，只要数据集足够，最终都会收敛到相似点。此外，文章还讨论了2023年机器学习的现状，包括模型在图像、文本、音频和视频方面的局限性，强调了数据质量和泛化能力的重要性。计算乘数的概念也被提出，它是衡量学习算法效率的重要指标，对于降低成本和提升模型性能具有重大意义。
文章目录
人工智能模型中的“它”是数据集。 The “it” in AI models is the dataset.
I’ve been at OpenAI for almost a year now. In that time, I’ve trained a lot of generative models. More than anyone really has any right to train. As I’ve spent these hours observing the effects of tweaking various model configurations and hyperparameters, one thing that has struck me is the similarities in between all the training runs.
我在 OpenAI 工作已经快一年了。那段时间，我训练了很多生成模型。比任何人都更有权利接受训练。当我花了几个小时观察调整各种模型配置和超参数的效果时，令我印象深刻的一件事是所有训练运行之间的相似性。
It’s becoming awfully clear to me that these models are truly approximating their datasets to an incredible degree. What that means is not only that they learn
订阅专栏 解锁全文
扫一扫
82
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
