Search Results for author:
Found 17 papers, 9 papers with code
TSViz: Demystification of Deep Learning Models for Time-Series Analysis
This is a step towards making informed/explainable decisions in the domain of time-series, powered by deep learning.
Deep One-Class Classification
Despite the great advances made by deep learning in many machine learning problems, there is a relative dearth of deep learning approaches for anomaly detection.
Ranked #32 on
Anomaly Detection
on One-class CIFAR-10
DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series
In contrast to the anomaly detection methods where anomalies are learned, DeepAnT uses unlabeled data to capture and learn the data distribution that is used to forecast the normal behavior of a time series.
KINN: Incorporating Expert Knowledge in Neural Networks
The promise of ANNs to automatically discover and extract useful features/patterns from data without dwelling on domain expertise although seems highly promising but comes at the cost of high reliance on large amount of accurately labeled data, which is often hard to acquire and formulate especially in time-series domains like anomaly detection, natural disaster management, predictive maintenance and healthcare.
TSXplain: Demystification of DNN Decisions for Time-Series using Natural Language and Statistical Features
This indicates a vital gap between the explainability provided by the systems and the novice user.
TSInsight: A local-global attribution framework for interpretability in time-series data
We approach the problem of interpretability in a novel way by proposing TSInsight where we attach an auto-encoder to the classifier with a sparsity-inducing norm on its output and fine-tune it based on the gradients from the classifier and a reconstruction penalty.
Interpreting Deep Models through the Lens of Data
Identification of input data points relevant for the classifier (i. e. serve as the support vector) has recently spurred the interest of researchers for both interpretability as well as dataset debugging.
Two-stage framework for optic disc localization and glaucoma classification in retinal fundus images using deep learning
For glaucoma classification we achieved AUC equal to 0. 874 which is 2. 7% relative improvement over the state-of-the-art results previously obtained for classification on ORIGA.
Benchmarking adversarial attacks and defenses for time-series data
This paves the way for future research in the direction of adversarial attacks and defenses, particularly for time-series data.
Going Beyond Classification Accuracy Metrics in Model Compression
With the rise in edge-computing devices, there has been an increasing demand to deploy energy and resource-efficient models.
Identifying Layers Susceptible to Adversarial Attacks
In this paper, we investigate the use of pretraining with adversarial networks, with the objective of discovering the relationship between network depth and robustness.
Improving Health Mentioning Classification of Tweets using Contrastive Adversarial Training
The idea is to learn word representation by its surrounding words and utilize emojis in the text to help improve the classification results.
Revisiting the Shape-Bias of Deep Learning for Dermoscopic Skin Lesion Classification
Interestingly, despite deep feature extractors being inclined towards learning entangled features for skin lesion classification, individual features can still be decoded from this entangled representation.
Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics
Modern machine learning research relies on relatively few carefully curated datasets.
Domain Generalization for Robust Model-Based Offline Reinforcement Learning
Existing offline reinforcement learning (RL) algorithms typically assume that training data is either: 1) generated by a known policy, or 2) of entirely unknown origin.
Blockwise Self-Supervised Learning at Scale
Current state-of-the-art deep networks are all powered by backpropagation.
Investigating the Nature of 3D Generalization in Deep Neural Networks
Modern deep learning architectures for object recognition generalize well to novel views, but the mechanisms are not well understood.
