Parts of the brain that carry sensory tasks are organized topographically: nearby neurons are responsive to the same properties of input signals. Thus, in this work, inspired by the neuroscience literature, we proposed a new topographic inductive bias in Convolutional Neural Networks (CNNs). To achieve this, we introduced a new topographic loss and an efficient implementation to topographically organize each convolutional layer of any CNN. We benchmarked our new method on 4 datasets and 3 models in vision and audio tasks and showed equivalent performance to all benchmarks. Besides, we also showcased the generalizability of our topographic loss with how it can be used with different topographic organizations in CNNs. Finally, we demonstrated that adding the topographic inductive bias made CNNs more resistant to pruning. Our approach provides a new avenue to obtain models that are more memory efficient while maintaining better accuracy.
翻译:带有感官任务的大脑部分是按地形排列的:附近的神经元对输入信号的相同特性作出反应。因此,在这一工作中,在神经科学文献的启发下,我们建议在进化神经网络(CNNs)中出现一种新的地形感应偏差。为了实现这一目标,我们引入了新的地形损失,并有效地实施了地形感应组织任何CNN的每个进化层。我们用4个数据集和3个视觉和音频任务模型作为我们新方法的基准,并展示了与所有基准相当的性能。此外,我们还展示了我们地形损失的可概括性,说明了如何在CNN的不同地形组织中使用它。最后,我们展示了添加地形感应偏差使CNN更能耐乱。我们的方法为获得在保持更准确性的同时更高效的记忆模型提供了新的途径。