arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.07917cs.NEcs.AIcs.LG
收藏

鲍德温效应(Baldwin Effect)

Meta-Learning by the Baldwin Effect

Google DeepMind(谷歌DeepMind)

Chrisantha Thomas Fernando, Jakub Sygnowski, Simon Osindero, Jane Wang, Tom Schaul, Denis Teplyashin, Pablo Sprechmann, Alexander Pritzel, Andrei A. Rusu

摘要:

鲍德温效应的范围最近受到两篇论文的质疑,这两篇论文仔细研究了辛顿和诺兰的开创性工作。到目前为止,还没有证据表明它在经验上具有挑战性的任务中的必要性。在这里,我们证明了鲍德温效应能够通过塑造深度学习算法的超参数和初始参数来发展Few-Shot监督和强化学习机制。此外,它可以在遗传上适应与最近称为MAML“模型不可知元学习”的机器学习算法相同的问题集上的强学习偏差,该算法使用二阶梯度而不是进化来学习一组参考参数(初始权重),可以快速适应从分布中采样的任务。虽然在简单的情况下,MAML比Baldwin效应更有效,但Baldwin效应更普遍,因为它不需要将梯度反向传播到参考参数或超参数,并且允许在内部循环中有效地进行任何数量的梯度更新。鲍德温效应学习强烈的学习依赖性偏见,而不是纯粹的遗传适应固定的行为在学习独立的方式。

英文摘要:

The scope of the Baldwin effect was recently called into question by two papers that closely examined the seminal work of Hinton and Nowlan. To this date there has been no demonstration of its necessity in empirically challenging tasks. Here we show that the Baldwin effect is capable of evolving few-shot supervised and reinforcement learning mechanisms, by shaping the hyperparameters and the initial parameters of deep learning algorithms. Furthermore it can genetically accommodate strong learning biases on the same set of problems as a recent machine learning algorithm called MAML "Model Agnostic Meta-Learning" which uses second-order gradients instead of evolution to learn a set of reference parameters (initial weights) that can allow rapid adaptation to tasks sampled from a distribution. Whilst in simple cases MAML is more data efficient than the Baldwin effect, the Baldwin effect is more general in that it does not require gradients to be backpropagated to the reference parameters or hyperparameters, and permits effectively any number of gradient updates in the inner loop. The Baldwin effect learns strong learning dependent biases, rather than purely genetically accommodating fixed behaviours in a learning independent manner.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑