Search Results for author: Kiran Karra

Found 12 papers, 2 papers with code

Kullback-Leibler Divergence-Guided Copula Statistics-Based Blind Source Separation of Dependent Signals

no code implementations14 Sep 2023 Pooja Algikar, Lamine Mili, Kiran Karra, Mohsen Ben Hassine

In this paper, we propose a blind source separation of a linear mixture of dependent sources based on copula statistics that measure the non-linear dependence between source component signals structured as copula density functions.

Context-Adaptive Deep Neural Networks via Bridge-Mode Connectivity

no code implementations28 Nov 2022 Nathan Drenkow, Alvin Tan, Chace Ashcraft, Kiran Karra

The deployment of machine learning models in safety-critical applications comes with the expectation that such models will perform well over a range of contexts (e. g., a vision model for classifying street signs should work in rural, city, and highway settings under varying lighting/weather conditions).

Image Classification

Machine Learning aided Crop Yield Optimization

no code implementations1 Nov 2021 Chace Ashcraft, Kiran Karra

We present a crop simulation environment with an OpenAI Gym interface, and apply modern deep reinforcement learning (DRL) algorithms to optimize yield.

BIG-bench Machine Learning OpenAI Gym +2

SanitAIs: Unsupervised Data Augmentation to Sanitize Trojaned Neural Networks

no code implementations9 Sep 2021 Kiran Karra, Chace Ashcraft, Cash Costello

Self-supervised learning (SSL) methods have resulted in broad improvements to neural network performance by leveraging large, untapped collections of unlabeled data to learn generalized underlying structure.

Data Augmentation Self-Supervised Learning

Poisoning Deep Reinforcement Learning Agents with In-Distribution Triggers

no code implementations14 Jun 2021 Chace Ashcraft, Kiran Karra

In this paper, we propose a new data poisoning attack and apply it to deep reinforcement learning agents.

Data Poisoning Multi-Task Learning +2

Speaker Diarization using Two-pass Leave-One-Out Gaussian PLDA Clustering of DNN Embeddings

1 code implementation6 Apr 2021 Kiran Karra, Alan McCree

Many modern systems for speaker diarization, such as the recently-developed VBx approach, rely on clustering of DNN speaker embeddings followed by resegmentation.

Clustering speaker-diarization +1

The TrojAI Software Framework: An OpenSource tool for Embedding Trojans into Deep Learning Models

1 code implementation13 Mar 2020 Kiran Karra, Chace Ashcraft, Neil Fendley

In this paper, we introduce the TrojAI software framework, an open source set of Python tools capable of generating triggered (poisoned) datasets and associated deep learning (DL) models with trojans at scale.

An Empirical Assessment of the Complexity and Realism of Synthetic Social Contact Networks

no code implementations6 Oct 2018 Kiran Karra, Samarth Swarup, Justus Graham

We use multiple measures of graph complexity to evaluate the realism of synthetically-generated networks of human activity, in comparison with several stylized network models as well as a collection of empirical networks from the literature.

On the Effect of Suboptimal Estimation of Mutual Information in Feature Selection and Classification

no code implementations30 Apr 2018 Kiran Karra, Lamine Mili

This paper introduces a new property of estimators of the strength of statistical association, which helps characterize how well an estimator will perform in scenarios where dependencies between continuous and discrete random variables need to be rank ordered.

feature selection General Classification

Learning Approximate Neural Estimators for Wireless Channel State Information

no code implementations19 Jul 2017 Timothy J. O'Shea, Kiran Karra, T. Charles Clancy

Estimation is a critical component of synchronization in wireless and signal processing systems.

Copula Index for Detecting Dependence and Monotonicity between Stochastic Signals

no code implementations20 Mar 2017 Kiran Karra, Lamine Mili

This paper introduces a nonparametric copula-based index for detecting the strength and monotonicity structure of linear and nonlinear statistical dependence between pairs of random variables or stochastic signals.

Learning to Communicate: Channel Auto-encoders, Domain Specific Regularizers, and Attention

no code implementations23 Aug 2016 Timothy J. O'Shea, Kiran Karra, T. Charles Clancy

We address the problem of learning efficient and adaptive ways to communicate binary information over an impaired channel.

Cannot find the paper you are looking for? You can Submit a new open access paper.