Search Results for author:
Found 10 papers, 5 papers with code
Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Objectives
We find that current state-of-the-art empirical techniques offer sub-optimal performance on these practical, non-decomposable performance objectives.
Deep Mapper: Efficient Visualization of Plausible Conformational Pathways
In our numerical experiments, based on an isometric latent space built on the common 50S-ribosomal dataset, the resulting Mapper graph successfully includes all the well-recognized plausible pathways.
Cost-Sensitive Self-Training for Optimizing Non-Decomposable Metrics
Using the proposed CSST framework, we obtain practical self-training methods (for both vision and NLP tasks) for optimizing different non-decomposable metrics using deep neural networks.
Fast and Multi-aspect Mining of Complex Time-stamped Event Streams
Thanks to its concise but effective summarization, CubeScope can also detect the sudden appearance of anomalies and identify the types of anomalies that occur in practice.
Toward Unlimited Self-Learning MCMC with Parallel Adaptive Annealing
However, SLMC methods are difficult to directly apply to multimodal distributions for which training data are difficult to obtain.
Topological Uncertainty: Monitoring trained neural networks through persistence of activation graphs
We showcase experimentally the potential of Topological Uncertainty in the context of trained network selection, Out-Of-Distribution detection, and shift-detection, both on synthetic and real datasets of images and graphs.
Application of Topological Data Analysis to Delirium Detection
We propose a new scoring algorithm for detecting delirium from one-channel EEG, based on topological data analysis.
Topological Data Analysis for Arrhythmia Detection through Modular Neural Networks
This paper presents an innovative and generic deep learning approach to monitor heart conditions from ECG signals. We focus our attention on both the detection and classification of abnormal heartbeats, known as arrhythmia.
PersLay: A Neural Network Layer for Persistence Diagrams and New Graph Topological Signatures
Persistence diagrams, the most common descriptors of Topological Data Analysis, encode topological properties of data and have already proved pivotal in many different applications of data science.
DTM-based Filtrations
Despite strong stability properties, the persistent homology of filtrations classically used in Topological Data Analysis, such as, e. g. the Cech or Vietoris-Rips filtrations, are very sensitive to the presence of outliers in the data from which they are computed.
Computational Geometry Algebraic Topology
