TRIER: Template-Guided Neural Networks for Robust and Interpretable Sleep Stage Identification from EEG Recordings

• URL: http://arxiv.org/abs/2009.05407v1
• Date: Thu, 10 Sep 2020 01:58:06 GMT
• Title: TRIER: Template-Guided Neural Networks for Robust and Interpretable Sleep Stage Identification from EEG Recordings
• Authors: Taeheon Lee, Jeonghwan Hwang, Honggu Lee
• Abstract summary: In this study, we propose a pre-training technique that handles this challenge in sleep staging tasks. Inspired by conventional methods that experienced physicians have used to classify sleep states, our method introduces a cosine similarity based convolutional neural network. We show that guiding a neural network with template patterns is an effective approach for sleep staging, since (1) classification performances are significantly enhanced and (2) robustness in several aspects are improved.
• Score: 5.156484100374058
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural networks often obtain sub-optimal representations during training, which degrade robustness as well as classification performances. This is a severe problem in applying deep learning to bio-medical domains, since models are vulnerable to being harmed by irregularities and scarcities in data. In this study, we propose a pre-training technique that handles this challenge in sleep staging tasks. Inspired by conventional methods that experienced physicians have used to classify sleep states from the existence of characteristic waveform shapes, or template patterns, our method introduces a cosine similarity based convolutional neural network to extract representative waveforms from training data. Afterwards, these features guide a model to construct representations based on template patterns. Through extensive experiments, we demonstrated that guiding a neural network with template patterns is an effective approach for sleep staging, since (1) classification performances are significantly enhanced and (2) robustness in several aspects are improved. Last but not least, interpretations on models showed that notable features exploited by trained experts are correctly addressed during prediction in the proposed method.

Related papers

• Adversarial Robustification via Text-to-Image Diffusion Models [56.37291240867549]
  Adrial robustness has been conventionally believed as a challenging property to encode for neural networks. We develop a scalable and model-agnostic solution to achieve adversarial robustness without using any data.
  arXiv  Detail & Related papers  (2024-07-26T10:49:14Z)
• SINDER: Repairing the Singular Defects of DINOv2 [61.98878352956125]
  Vision Transformer models trained on large-scale datasets often exhibit artifacts in the patch token they extract. We propose a novel fine-tuning smooth regularization that rectifies structural deficiencies using only a small dataset.
  arXiv  Detail & Related papers  (2024-07-23T20:34:23Z)
• MENTOR: Human Perception-Guided Pretraining for Increased Generalization [5.596752018167751]
  We introduce MENTOR (huMan pErceptioN-guided preTraining fOr increased geneRalization) We train an autoencoder to learn human saliency maps given an input image, without class labels. We remove the decoder part, add a classification layer on top of the encoder, and fine-tune this new model conventionally.
  arXiv  Detail & Related papers  (2023-10-30T13:50:44Z)
• An interpretable deep learning method for bearing fault diagnosis [12.069344716912843]
  We utilize a convolutional neural network (CNN) with Gradient-weighted Class Activation Mapping (Grad-CAM) visualizations to form an interpretable Deep Learning (DL) method for classifying bearing faults. During the model evaluation process, the proposed approach retrieves prediction basis samples from the health library according to the similarity of the feature importance.
  arXiv  Detail & Related papers  (2023-08-20T15:22:08Z)
• How neural networks learn to classify chaotic time series [77.34726150561087]
  We study the inner workings of neural networks trained to classify regular-versus-chaotic time series. We find that the relation between input periodicity and activation periodicity is key for the performance of LKCNN models.
  arXiv  Detail & Related papers  (2023-06-04T08:53:27Z)
• ShapeWordNet: An Interpretable Shapelet Neural Network for Physiological Signal Classification [16.82411861562806]
  We propose a more effective and interpretable scheme tailored for the physiological signal classification task. We exploit the time series shapelets to extract prominent local patterns and perform interpretable sequence discretization. We name our method as ShapeWordNet and conduct extensive experiments on three real-world datasets to investigate its effectiveness.
  arXiv  Detail & Related papers  (2023-02-10T02:30:31Z)
• Reconciliation of Pre-trained Models and Prototypical Neural Networks in Few-shot Named Entity Recognition [35.34238362639678]
  We propose a one-line-code normalization method to reconcile such a mismatch with empirical and theoretical grounds. Our work also provides an analytical viewpoint for addressing the general problems in few-shot name entity recognition.
  arXiv  Detail & Related papers  (2022-11-07T02:33:45Z)
• A novel approach for wafer defect pattern classification based on topological data analysis [0.0]
  In semiconductor manufacturing, wafer map defect pattern provides critical information for facility maintenance and yield management. We propose a novel way to represent the shape of the defect pattern as a finite-dimensional vector, which will be used as an input for a neural network algorithm for classification.
  arXiv  Detail & Related papers  (2022-09-19T11:54:13Z)
• Ultrasound Signal Processing: From Models to Deep Learning [64.56774869055826]
  Medical ultrasound imaging relies heavily on high-quality signal processing to provide reliable and interpretable image reconstructions. Deep learning based methods, which are optimized in a data-driven fashion, have gained popularity. A relatively new paradigm combines the power of the two: leveraging data-driven deep learning, as well as exploiting domain knowledge.
  arXiv  Detail & Related papers  (2022-04-09T13:04:36Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Automatic Recall Machines: Internal Replay, Continual Learning and the Brain [104.38824285741248]
  Replay in neural networks involves training on sequential data with memorized samples, which counteracts forgetting of previous behavior caused by non-stationarity. We present a method where these auxiliary samples are generated on the fly, given only the model that is being trained for the assessed objective. Instead the implicit memory of learned samples within the assessed model itself is exploited.
  arXiv  Detail & Related papers  (2020-06-22T15:07:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.