TopoAct: Visually Exploring the Shape of Activations in Deep Learning
arXiv:1912.06332
Abstract
Deep neural networks such as GoogLeNet, ResNet, and BERT have achieved impressive performance in tasks such as image and text classification. To understand how such performance is achieved, we probe a trained deep neural network by studying neuron activations, i.e., combinations of neuron firings, at various layers of the network in response to a particular input. With a large number of inputs, we aim to obtain a global view of what neurons detect by studying their activations. In particular, we develop visualizations that show the shape of the activation space, the organizational principle behind neuron activations, and the relationships of these activations within a layer. Applying tools from topological data analysis, we present TopoAct, a visual exploration system to study topological summaries of activation vectors. We present exploration scenarios using TopoAct that provide valuable insights into learned representations of neural networks. We expect TopoAct to give a topological perspective that enriches the current toolbox of neural network analysis, and to provide a basis for network architecture diagnosis and data anomaly detection.
References in corpus (10)
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
- BioBERT: a pre-trained biomedical language representation model for biomedical text mining
- Understanding Neural Networks Through Deep Visualization
- Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images
- Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks
- Topology of Learning in Artificial Neural Networks
- Persistent Homology Guided Force-Directed Graph Layouts
- Adposition and Case Supersenses v2.6: Guidelines for English
- Homology-Preserving Dimensionality Reduction via Manifold Landmarking and Tearing
- Mapper Interactive: A Scalable, Extendable, and Interactive Toolbox for the Visual Exploration of High-Dimensional Data