no code implementations • 23 Mar 2024 • Mohammad Mahmudul Alam, Edward Raff, Stella Biderman, Tim Oates, James Holt
Malware detection is an interesting and valuable domain to work in because it has significant real-world impact and unique machine-learning challenges.
no code implementations • 13 Mar 2024 • Khondoker Murad Hossain, Tim Oates
In the rapidly evolving landscape of communication and network security, the increasing reliance on deep neural networks (DNNs) and cloud services for data processing presents a significant vulnerability: the potential for backdoors that can be exploited by malicious actors.
no code implementations • 6 Jan 2024 • Khondoker Murad Hossain, Tim Oates
As deep neural networks and the datasets used to train them get larger, the default approach to integrating them into research and commercial projects is to download a pre-trained model and fine tune it.
1 code implementation • 23 Dec 2023 • Mohammad Mahmudul Alam, Edward Raff, Tim Oates
While deep learning has enjoyed significant success in computer vision tasks over the past decade, many shortcomings still exist from a Cognitive Science (CogSci) perspective.
1 code implementation • 2 Dec 2023 • Mohammad Mahmudul Alam, Edward Raff, Tim Oates, Cynthia Matuszek
In the case of DDx, the proposed network has achieved a mean accuracy of 99. 82% and a mean F1 score of 0. 9472.
1 code implementation • 9 Nov 2023 • Bharat Prakash, Tim Oates, Tinoosh Mohsenin
However, using LLMs to solve real world problems is hard because they are not grounded in the current task.
1 code implementation • 28 Jun 2023 • Corey J. Nolet, Divye Gala, Alex Fender, Mahesh Doijade, Joe Eaton, Edward Raff, John Zedlewski, Brad Rees, Tim Oates
In this paper, we propose cuSLINK, a novel and state-of-the-art reformulation of the SLINK algorithm on the GPU which requires only $O(Nk)$ space and uses a parameter $k$ to trade off space and time.
1 code implementation • 31 May 2023 • Mohammad Mahmudul Alam, Edward Raff, Stella Biderman, Tim Oates, James Holt
In recent years, self-attention has become the dominant paradigm for sequence modeling in a variety of domains.
no code implementations • 13 Feb 2023 • Sourajit Saha, Shaswati Saha, Md Osman Gani, Tim Oates, David Chapman
Learning High-Resolution representations is essential for semantic segmentation.
no code implementations • 15 Dec 2022 • Khondoker Murad Hossain, Tim Oates
The increasing importance of both deep neural networks (DNNs) and cloud services for training them means that bad actors have more incentive and opportunity to insert backdoors to alter the behavior of trained models.
no code implementations • 23 Nov 2022 • Rebecca Saul, Mohammad Mahmudul Alam, John Hurwitz, Edward Raff, Tim Oates, James Holt
Recurrent neural nets have been successful in processing sequences for a number of tasks; however, they are known to be both ineffective and computationally expensive when applied to very long sequences.
no code implementations • 16 Oct 2022 • Bharat Prakash, Nicholas Waytowich, Tim Oates, Tinoosh Mohsenin
Learning to solve long horizon temporally extended tasks with reinforcement learning has been a challenge for several years now.
1 code implementation • 13 Jun 2022 • Mohammad Mahmudul Alam, Edward Raff, Tim Oates, James Holt
Due to the computational cost of running inference for a neural network, the need to deploy the inferential steps on a third party's compute environment or hardware is common.
no code implementations • 7 Nov 2021 • Bharat Prakash, Nicholas Waytowich, Tinoosh Mohsenin, Tim Oates
In this work, we propose a method for automatic goal generation using a dynamical distance function (DDF) in a self-supervised fashion.
no code implementations • 9 Oct 2021 • Bharat Prakash, Nicholas Waytowich, Tim Oates, Tinoosh Mohsenin
The low-level controller executes the sub-tasks based on the language commands.
no code implementations • 30 Sep 2021 • Sourav Mukherjee, David Widmark, Vince DiMascio, Tim Oates
Accurate specification of standard occupational classification (SOC) code is critical to the success of many U. S. work visa applications.
1 code implementation • NeurIPS 2021 • Ashwinkumar Ganesan, Hang Gao, Sunil Gandhi, Edward Raff, Tim Oates, James Holt, Mark McLean
HRRs today are not effective in a differentiable solution due to numerical instability, a problem we solve by introducing a projection step that forces the vectors to exist in a well behaved point in space.
no code implementations • Findings (ACL) 2021 • Ashwinkumar Ganesan, Francis Ferraro, Tim Oates
We propose a Bi-Directional Manifold Alignment (BDMA) that learns a non-linear mapping between two manifolds by explicitly training it to be bijective.
2 code implementations • 13 Apr 2021 • Corey J. Nolet, Divye Gala, Edward Raff, Joe Eaton, Brad Rees, John Zedlewski, Tim Oates
High-performance primitives for mathematical operations on sparse vectors must deal with the challenges of skewed degree distributions and limits on memory consumption that are typically not issues in dense operations.
no code implementations • 29 Sep 2020 • Sourav Mukherjee, Tim Oates, Vince DiMascio, Huguens Jean, Rob Ares, David Widmark, Jaclyn Harder
In this paper, we consider the problem of organizing supporting documents vital to U. S. work visa petitions, as well as responding to Requests For Evidence (RFE) issued by the U. S.~Citizenship and Immigration Services (USCIS).
1 code implementation • 1 Aug 2020 • Corey J. Nolet, Victor Lafargue, Edward Raff, Thejaswi Nanditale, Tim Oates, John Zedlewski, Joshua Patterson
The Uniform Manifold Approximation and Projection (UMAP) algorithm has become widely popular for its ease of use, quality of results, and support for exploratory, unsupervised, supervised, and semi-supervised learning.
no code implementations • EACL (AdaptNLP) 2021 • Ashwinkumar Ganesan, Francis Ferraro, Tim Oates
We present a locality preserving loss (LPL) that improves the alignment between vector space embeddings while separating uncorrelated representations.
no code implementations • 10 Oct 2019 • Hang Gao, Tim Oates
Given a state-of-the-art deep neural network text classifier, we show the existence of a universal and very small perturbation vector (in the embedding space) that causes natural text to be misclassified with high probability.
no code implementations • 10 Oct 2019 • Karan K. Budhraja, Hang Gao, Tim Oates
A low time-complexity and data requirement favoring framework for reproducing emergent behavior, given an abstract demonstration, is discussed in [1], [2].
no code implementations • 29 Sep 2019 • Sunil Gandhi, Tim Oates, Tinoosh Mohsenin, Nicholas Waytowich
In this paper, we present a method for learning from video demonstrations by using human feedback to construct a mapping between the standard representation of the agent and the visual representation of the demonstration.
no code implementations • 12 Sep 2019 • Chi Zhang, Bryan Wilkinson, Ashwinkumar Ganesan, Tim Oates
Another way to remove that limitation, an optional classification layer, trained on manually annotated DoS attack tweets, to filter out non-attack tweets can be used to increase precision at the expense of recall.
no code implementations • 8 Aug 2019 • Sourav Mukherjee, Tim Oates, Ryan Wright
In this paper, we demonstrate that semantic information can play a useful role in computing graph embeddings.
no code implementations • 18 Apr 2019 • Isaac Mativo, Yelena Yesha, Michael Grasso, Tim Oates, Qian Zhu
The use of artificial intelligence in clinical care to improve decision support systems is increasing.
no code implementations • 28 Mar 2019 • Ashwinkumar Ganesan, Pooja Parameshwarappa, Akshay Peshave, ZhiYuan Chen, Tim Oates
In this paper, we proposeaprobabilistic abductive reasoningapproach that augments an exist-ing rule-based IDS (snort [29]) to detect these evolved attacks by (a)Predicting rule conditions that are likely to occur (based on existingrules) and (b) able to generate new snort rules when provided withseed rule (i. e. a starting rule) to reduce the burden on experts toconstantly update them.
no code implementations • 25 Mar 2019 • Bharat Prakash, Mark Horton, {Nicholas R. Waytowich, William David Hairston, Tim Oates, Tinoosh Mohsenin
This compression model is vital to efficiently learn policies, especially when learning on embedded systems.
no code implementations • Advances in Knowledge Discovery and Data Mining. PAKDD 2018 2018 • Sunil Gandhi, Tim Oates, Tinoosh Mohsenin, David Hairston
This step is especially important if the noise in data originates from diverse sources.
1 code implementation • 13 Sep 2017 • Zhiguang Wang, Chul Gwon, Tim Oates, Adam Iezzi
As the use of cloud computing continues to rise, controlling cost becomes increasingly important.
no code implementations • 28 Aug 2017 • JT Turner, Adam Page, Tinoosh Mohsenin, Tim Oates
Ubiquitous bio-sensing for personalized health monitoring is slowly becoming a reality with the increasing availability of small, diverse, robust, high fidelity sensors.
no code implementations • 31 Jul 2017 • Prutha Date, Ashwinkumar Ganesan, Tim Oates
Convolutional Neural Networks have been highly successful in performing a host of computer vision tasks such as object recognition, object detection, image segmentation and texture synthesis.
no code implementations • 13 Jun 2017 • Mandar Haldekar, Ashwinkumar Ganesan, Tim Oates
Traditional approaches to building a large scale knowledge graph have usually relied on extracting information (entities, their properties, and relations between them) from unstructured text (e. g. Dbpedia).
11 code implementations • 20 Nov 2016 • Zhiguang Wang, Weizhong Yan, Tim Oates
We propose a simple but strong baseline for time series classification from scratch with deep neural networks.
no code implementations • 9 Aug 2016 • Karan K. Budhraja, Tim Oates
One approach to Learning from Demonstration is Inverse Reinforcement Learning, in which actions are observed to infer rewards.
no code implementations • 13 Oct 2015 • Zhiguang Wang, Tim Oates, James Lo
We generalized a modified exponentialized estimator by pushing the robust-optimal (RO) index $\lambda$ to $-\infty$ for achieving robustness to outliers by optimizing a quasi-Minimin function.
no code implementations • 24 Sep 2015 • Zhiguang Wang, Tim Oates
We propose an off-line approach to explicitly encode temporal patterns spatially as different types of images, namely, Gramian Angular Fields and Markov Transition Fields.
no code implementations • 8 Jun 2015 • Zhiguang Wang, Tim Oates, James Lo
This paper proposes a set of new error criteria and learning approaches, Adaptive Normalized Risk-Averting Training (ANRAT), to attack the non-convex optimization problem in training deep neural networks (DNNs).
4 code implementations • 1 Jun 2015 • Zhiguang Wang, Tim Oates
We used Tiled Convolutional Neural Networks (tiled CNNs) on 20 standard datasets to learn high-level features from the individual and compound GASF-GADF-MTF images.
no code implementations • 19 Dec 2014 • Siddharth Pramod, Adam Page, Tinoosh Mohsenin, Tim Oates
We explore the use of neural networks trained with dropout in predicting epileptic seizures from electroencephalographic data (scalp EEG).