基于目标传播的语言模型训练
Training Language Models Using Target-Propagation
摘要:
虽然截断时间反向传播(BPTT)是训练递归神经网络(RNN)最流行的方法,但它具有固有的顺序性(使得并行化困难),并且在遥远的时间步长之间截断梯度流。我们调查是否目标传播(TPROP)风格的方法可以解决这些缺点。不幸的是,大量的实验表明,TPROP一般表现不佳BPTT,我们结束了这种现象的分析,并为今后的工作提出建议。
英文摘要:
While Truncated Back-Propagation through Time (BPTT) is the most popular approach to training Recurrent Neural Networks (RNNs), it suffers from being inherently sequential (making parallelization difficult) and from truncating gradient flow between distant time-steps. We investigate whether Target Propagation (TPROP) style approaches can address these shortcomings. Unfortunately, extensive experiments suggest that TPROP generally underperforms BPTT, and we end with an analysis of this phenomenon, and suggestions for future work.
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。