Improving the Robustness of Neural Multiplication Units with Reversible Stochasticity

arxiv(2022)

引用 0|浏览2
暂无评分
摘要
Multilayer Perceptrons struggle to learn certain simple arithmetic tasks. Specialist neural modules for arithmetic can outperform classical architectures with gains in extrapolation, interpretability and convergence speeds, but are highly sensitive to the training range. In this paper, we show that Neural Multiplication Units (NMUs) are unable to reliably learn tasks as simple as multiplying two inputs when given different training ranges. Causes of failure are linked to inductive and input biases which encourage convergence to solutions in undesirable optima. A solution, the stochastic NMU (sNMU), is proposed to apply reversible stochasticity, encouraging avoidance of such optima whilst converging to the true solution. Empirically, we show that stochasticity provides improved robustness with the potential to improve learned representations of upstream networks for numerical and image tasks.
更多
查看译文
关键词
neural multiplication units,stochasticity,robustness
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要