论文标题
在卷积神经网络中引入地形
Introducing topography in convolutional neural networks
论文作者
论文摘要
携带感官任务的大脑部分是在地形上组织的：附近的神经元对输入信号的相同特性有反应。因此，在这项工作中，受神经科学文献的启发，我们提出了卷积神经网络（CNN）中新的地形感应偏见。为此，我们引入了新的地形损失和有效的实现，以在地形上组织任何CNN的每个卷积层。我们在视觉和音频任务中的4个数据集和3个模型上对新方法进行了基准测试，并显示出与所有基准测试的等效性能。此外，我们还通过如何与CNN中的不同地形组织一起使用地形损失的普遍性。最后，我们证明了添加地形电感偏置使CNNS对修剪具有更大的抵抗力。我们的方法提供了一种新的途径，以获得更有效的模型，同时保持更好的准确性。
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.
