Visualizing Deep Neural Networks for Speech Recognition with Learned Topographic Filter Maps
Year: 2019
Type: preprint
Abstract: The uninformative ordering of artificial neurons in Deep Neural Networks complicates visualizing activations in deeper layers. This is one reason why the internal structure of such models is very unintuitive. In neuroscience, activity of real brains can be visualized by highlighting active regions. Inspired by those techniques, we train a convolutional speech recognition model, where filters are arranged in a 2D grid and neighboring filters are similar to each other. We show, how those topographic filter maps visualize artificial neuron activations more intuitively. Moreover, we investigate, whether this causes phoneme-responsive neurons to be grouped in certain regions of the topographic map.
Source: arXiv (Cornell University)
Authors: Krug, Andreas, Stober, Sebastian
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2994180997