Search Results for author:
Found 33 papers, 19 papers with code
Single Word Change is All You Need: Designing Attacks and Defenses for Text Classifiers
Experimental results on 4 datasets and BERT and distilBERT classifiers show that SP-Defense improves \r{ho} by 14. 6% and 13. 9% and decreases the attack success rate of SP-Attack by 30. 4% and 21. 2% on two classifiers respectively, and decreases the attack success rate of existing attack methods that involve multiple-word perturbations.
Pyreal: A Framework for Interpretable ML Explanations
Users in many domains use machine learning (ML) predictions to help them make decisions.
Lessons from Usable ML Deployments and Application to Wind Turbine Monitoring
Through the applications of our lessons to this task, we hope to demonstrate the potential real-world impact of usable ML in the renewable energy domain.
Making the End-User a Priority in Benchmarking: OrionBench for Unsupervised Time Series Anomaly Detection
The framework provides universal abstractions to represent models, extensibility to add new pipelines and datasets, hyperparameter standardization, pipeline verification, and frequent releases with published benchmarks.
AER: Auto-Encoder with Regression for Time Series Anomaly Detection
We then propose AER (Auto-encoder with Regression), a joint model that combines a vanilla auto-encoder and an LSTM regressor to incorporate the successes and address the limitations of each method.
Sequential Models in the Synthetic Data Vault
After building the Sequential SDV, we used it to generate synthetic data and compared its quality against an existing, non-sequential generative adversarial network based model called CTGAN.
Sintel: A Machine Learning Framework to Extract Insights from Signals
The detection of anomalies in time series data is a critical task with many monitoring applications.
The Need for Interpretable Features: Motivation and Taxonomy
Through extensive experience developing and explaining machine learning (ML) applications for real-world domains, we have learned that ML models are only as interpretable as their features.
VBridge: Connecting the Dots Between Features and Data to Explain Healthcare Models
Machine learning (ML) is increasingly applied to Electronic Health Records (EHRs) to solve clinical prediction tasks.
R&R: Metric-guided Adversarial Sentence Generation
It improves the quality of adversarial examples by optimizing a critique score which combines the fluency, similarity, and misclassification metrics.
Sibyl: Understanding and Addressing the Usability Challenges of Machine Learning In High-Stakes Decision Making
Machine learning (ML) is being applied to a diverse and ever-growing set of domains.
Enabling Collaborative Data Science Development with the Ballet Framework
While the open-source software development model has led to successful large-scale collaborations in building software systems, data science projects are frequently developed by individuals or small teams.
Rewriting Meaningful Sentences via Conditional BERT Sampling and an application on fooling text classifiers
Most adversarial attack methods that are designed to deceive a text classifier change the text classifier's prediction by modifying a few words or characters.
AutoML to Date and Beyond: Challenges and Opportunities
AutoML tools aim to make machine learning accessible for non-machine learning experts (domain experts), to improve the efficiency of machine learning, and to accelerate machine learning research.
Cardea: An Open Automated Machine Learning Framework for Electronic Health Records
An estimated 180 papers focusing on deep learning and EHR were published between 2010 and 2018.
TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks
However, detecting anomalies in time series data is particularly challenging due to the vague definition of anomalies and said data's frequent lack of labels and highly complex temporal correlations.
TILM: Neural Language Models with Evolving Topical Influence
Specifically, we propose a novel language model called Topical Influence Language Model (TILM), which is a novel extension of a neural language model to capture the influences on the contents in one text stream by the evolving topics in another related (or possibly same) text stream.
Adversarially learned anomaly detection for time series data
Based on the recent developments in adversarially learned models, we propose a new approach for anomaly detection in time series data.
Robust Invisible Video Watermarking with Attention
The goal of video watermarking is to embed a message within a video file in a way such that it minimally impacts the viewing experience but can be recovered even if the video is redistributed and modified, allowing media producers to assert ownership over their content.
Towards Reducing Biases in Combining Multiple Experts Online
In many real life situations, including job and loan applications, gatekeepers must make justified and fair real-time decisions about a person's fitness for a particular opportunity.
Modeling Tabular data using Conditional GAN
Tabular data usually contains a mix of discrete and continuous columns.
MLFriend: Interactive Prediction Task Recommendation for Event-Driven Time-Series Data
In this paper, we tackle the challenge of defining useful prediction problems on event-driven time-series data.
The Machine Learning Bazaar: Harnessing the ML Ecosystem for Effective System Development
To address these problems, we introduce the Machine Learning Bazaar, a new framework for developing machine learning and automated machine learning software systems.
ATMSeer: Increasing Transparency and Controllability in Automated Machine Learning
To guide the design of ATMSeer, we derive a workflow of using AutoML based on interviews with machine learning experts.
SteganoGAN: High Capacity Image Steganography with GANs
Image steganography is a procedure for hiding messages inside pictures.
Learning Vine Copula Models For Synthetic Data Generation
Moreover, we demonstrate that the model is able to generate high-quality samples in a variety of applications, making it a good candidate for synthetic data generation.
Prediction Factory: automated development and collaborative evaluation of predictive models
In a head-to-head trial, reports generated utilizing full data science automation interface reports were funded 57. 5% of the time, while the ones that used baseline automation were only funded 42. 5% of the time.
Synthesizing Tabular Data using Generative Adversarial Networks
Generative adversarial networks (GANs) implicitly learn the probability distribution of a dataset and can draw samples from the distribution.
Machine learning 2.0 : Engineering Data Driven AI Products
ML 2. 0: In this paper, we propose a paradigm shift from the current practice of creating machine learning models - which requires months-long discovery, exploration and "feasibility report" generation, followed by re-engineering for deployment - in favor of a rapid, 8-week process of development, understanding, validation and deployment that can executed by developers or subject matter experts (non-ML experts) using reusable APIs.
ATM: A distributed, collaborative, scalable system for automated machine learning
In this paper, we present Auto-Tuned Models, or ATM, a distributed, collaborative, scalable system for automated machine learning.
Solving the "false positives" problem in fraud prediction
In this paper, we present an automated feature engineering based approach to dramatically reduce false positives in fraud prediction.
Deep Feature Synthesis: Towards Automating Data Science Endeavors
In this paper, we develop the Data Science Machine, which is able to derive predictive models from raw data automatically.
Likely to stop? Predicting Stopout in Massive Open Online Courses
Even with more difficult prediction problems, such as predicting stop out at the end of the course with only one weeks' data, the models attained AUCs of 0. 7.
