Papers › TopoAct: Visually Exploring the Shape of Activations in Deep Learning

TopoAct: Visually Exploring the Shape of Activations in Deep Learning

13 Dec 2019arXiv:1912.06332archive 2025-07-28

Archit Rathore, Nithin Chalapathi, Sourabh Palande, Bei Wang

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.

PaperPDFCode

Code

architrathore/TopoAct officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Anomaly DetectionDeep LearningImage ClassificationText ClassificationTopological Data Analysistext-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAdamAttentionAttention DropoutAuxiliary ClassifierAverage PoolingBERTBatch NormalizationBottleneck Residual BlockConvolutionDense ConnectionsDropoutGlobal Average PoolingGoogLeNetInception ModuleKaiming InitializationLayer NormalizationLinear LayerLinear Warmup With Linear DecayLocal Response NormalizationMax PoolingMulti-Head AttentionReLUResidual BlockResidual ConnectionSoftmaxWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections