Publications (64)
Finding Representative Points in Multivariate Data Using PCA
Ashwinkumar Ganesan, Tim Oates, Matt Schmill
The idea of representation has been used in various fields of study from data analysis to political science. In this paper, we define representativeness and describe a method to is…
Detecting Epileptic Seizures from EEG Data using Neural Networks
Siddharth Pramod, Adam Page, Tinoosh Mohsenin +1
We explore the use of neural networks trained with dropout in predicting epileptic seizures from electroencephalographic data (scalp EEG). The input to the neural network is a 126…
Cognitive Techniques for Early Detection of Cybersecurity Events
Sandeep Narayanan, Ashwinkumar Ganesan, Karuna Joshi +3
The early detection of cybersecurity events such as attacks is challenging given the constantly evolving threat landscape. Even with advanced monitoring, sophisticated attackers ca…
Hierarchical Learning for Maze Navigation: Emergence of Mental Representations via Second-Order Learning
Shalima Binta Manir, Tim Oates
Mental representation, characterized by structured internal models mirroring external environments, is fundamental to advanced cognition but remains challenging to investigate empi…
MDToC: Metacognitive Dynamic Tree of Concepts for Boosting Mathematical Problem-Solving of Large Language Models
Tung Duong Ta, Tim Oates, Thien Van Luong +2
Despite advances in mathematical reasoning capabilities, Large Language Models (LLMs) still struggle with calculation verification when using established prompting techniques. We p…
TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networks
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…
Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline
Zhiguang Wang, Weizhong Yan, Tim Oates
We propose a simple but strong baseline for time series classification from scratch with deep neural networks. Our proposed baseline models are pure end-to-end without any heavy pr…
Fashioning with Networks: Neural Style Transfer to Design Clothes
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…
Holographic Global Convolutional Networks for Long-Range Prediction Tasks in Malware Detection
Mohammad Mahmudul Alam, Edward Raff, Stella Biderman +2
Malware detection is an interesting and valuable domain to work in because it has significant real-world impact and unique machine-learning challenges. We investigate existing long…
LLM-Guided Agentic Floor Plan Parsing for Accessible Indoor Navigation of Blind and Low-Vision People
Aydin Ayanzadeh, Tim Oates
Indoor navigation remains a critical accessibility challenge for the blind and low-vision (BLV) individuals, as existing solutions rely on costly per-building infrastructure. We pr…
Predicting the Performance of Graph Convolutional Networks with Spectral Properties of the Graph Laplacian
Shalima Binta Manir, Tim Oates
A common observation in the Graph Convolutional Network (GCN) literature is that stacking GCN layers may or may not result in better performance on tasks like node classification a…
DeBUGCN -- Detecting Backdoors in CNNs Using Graph Convolutional Networks
Akash Vartak, Khondoker Murad Hossain, Tim Oates
Deep neural networks (DNNs) are becoming commonplace in critical applications, making their susceptibility to backdoor (trojan) attacks a significant problem. In this paper, we int…
Trojans in Artificial Intelligence (TrojAI) Final Report
Kristopher W. Reese, Taylor Kulp-McDowall, Michael Majurski +68
The Intelligence Advanced Research Projects Activity (IARPA) launched the TrojAI program to confront an emerging vulnerability in modern artificial intelligence: the threat of AI T…
LLM Augmented Hierarchical Agents
Bharat Prakash, Tim Oates, Tinoosh Mohsenin
Solving long-horizon, temporally-extended tasks using Reinforcement Learning (RL) is challenging, compounded by the common practice of learning without prior knowledge (or tabula r…
Recasting Self-Attention with Holographic Reduced Representations
Mohammad Mahmudul Alam, Edward Raff, Stella Biderman +2
In recent years, self-attention has become the dominant paradigm for sequence modeling in a variety of domains. However, in domains with very long sequence lengths the $\mathcal{O}…
Lempel-Ziv Networks
Rebecca Saul, Mohammad Mahmudul Alam, John Hurwitz +3
Sequence processing has long been a central area of machine learning research. Recurrent neural nets have been successful in processing sequences for a number of tasks; however, th…
cuSLINK: Single-linkage Agglomerative Clustering on the GPU
Corey J. Nolet, Divye Gala, Alex Fender +6
In this paper, we propose cuSLINK, a novel and state-of-the-art reformulation of the SLINK algorithm on the GPU which requires only space and uses a parameter to trade…
Automated Cloud Provisioning on AWS using Deep Reinforcement Learning
Zhiguang Wang, Chul Gwon, Tim Oates +1
As the use of cloud computing continues to rise, controlling cost becomes increasingly important. Yet there is evidence that 30\% - 45\% of cloud spend is wasted. Existing tools fo…
Adopting Robustness and Optimality in Fitting and Learning
Zhiguang Wang, Tim Oates, James Lo
We generalized a modified exponentialized estimator by pushing the robust-optimal (RO) index to for achieving robustness to outliers by optimizing a quasi-Minimin fu…
One Model, Two Minds: A Context-Gated Graph Learner that Recreates Human Biases
Shalima Binta Manir, Tim Oates
We introduce a novel Theory of Mind (ToM) framework inspired by dual-process theories from cognitive science, integrating a fast, habitual graph-based reasoning system (System 1),…
Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representations
Mohammad Mahmudul Alam, Edward Raff, Tim Oates +1
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. If t…
Invariance-embedded Machine Learning Sub-grid-scale Stress Models for Meso-scale Hurricane Boundary Layer Flow Simulation I: Model Development and Studies
Md Badrul Hasan, Meilin Yu, Tim Oates
This study develops invariance-embedded machine learning sub-grid-scale (SGS) stress models admitting turbulence kinetic energy (TKE) backscatter towards more accurate large eddy s…
Towards an Interpretable Hierarchical Agent Framework using Semantic Goals
Bharat Prakash, Nicholas Waytowich, Tim Oates +1
Learning to solve long horizon temporally extended tasks with reinforcement learning has been a challenge for several years now. We believe that it is important to leverage both th…
Interactive Hierarchical Guidance using Language
Bharat Prakash, Nicholas Waytowich, Tim Oates +1
Reinforcement learning has been successful in many tasks ranging from robotic control, games, energy management etc. In complex real world environments with sparse rewards and long…
A Walsh Hadamard Derived Linear Vector Symbolic Architecture
Mohammad Mahmudul Alam, Alexander Oberle, Edward Raff +3
Vector Symbolic Architectures (VSAs) are one approach to developing Neuro-symbolic AI, where two vectors in are `bound' together to produce a new vector in the same…
Identifying Spatial Relations in Images using Convolutional Neural Networks
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 unstruc…
SBI-RAG: Enhancing Math Word Problem Solving for Students through Schema-Based Instruction and Retrieval-Augmented Generation
Prakhar Dixit, Tim Oates
Many students struggle with math word problems (MWPs), often finding it difficult to identify key information and select the appropriate mathematical operations. Schema-based instr…
ASEHybrid: When Geometry Matters Beyond Homophily in Graph Neural Networks
Shalima Binta Manir, Tim Oates
Standard message-passing graph neural networks (GNNs) often struggle on graphs with low homophily, yet homophily alone does not explain this behavior, as graphs with similar homoph…
Adaptive Normalized Risk-Averting Training For Deep Neural Networks
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 traini…
Locality Preserving Loss: Neighbors that Live together, Align together
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. Given two pretrained embeddin…
Automatic Goal Generation using Dynamical Distance Learning
Bharat Prakash, Nicholas Waytowich, Tinoosh Mohsenin +1
Reinforcement Learning (RL) agents can learn to solve complex sequential decision making tasks by interacting with the environment. However, sample efficiency remains a major chall…
Bringing UMAP Closer to the Speed of Light with GPU Acceleration
Corey J. Nolet, Victor Lafargue, Edward Raff +4
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, sup…
Backdoor Attack Detection in Computer Vision by Applying Matrix Factorization on the Weights of Deep Networks
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…
Advancing Security in AI Systems: A Novel Approach to Detecting Backdoors in Deep Neural Networks
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 si…
Determining Standard Occupational Classification Codes from Job Descriptions in Immigration Petitions
Sourav Mukherjee, David Widmark, Vince DiMascio +1
Accurate specification of standard occupational classification (SOC) code is critical to the success of many U.S. work visa applications. Determination of correct SOC code relies o…
Towards Scalable SOAP Note Generation: A Weakly Supervised Multimodal Framework
Sadia Kamal, Tim Oates, Joy Wan
Skin carcinoma is the most prevalent form of cancer globally, accounting for over $8 billion in annual healthcare expenditures. In clinical settings, physicians document patient vi…
Universal Adversarial Perturbation for Text Classification
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 t…
Honest Lying: Understanding Memory Confabulation in Reflexive Agents
Prakhar Dixit, Sadia Kamal, Tim Oates
Reflexion-style agents rely on self-generated reflections as memory, implicitly assuming that agents can accurately diagnose their own failures. We show that this assumption can fa…
Learning a Reversible Embedding Mapping using Bi-Directional Manifold Alignment
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. We demonstrate BDMA by train…
MedGrad E-CLIP: Enhancing Trust and Transparency in AI-Driven Skin Lesion Diagnosis
Sadia Kamal, Tim Oates
As deep learning models gain attraction in medical data, ensuring transparent and trustworthy decision-making is essential. In skin cancer diagnosis, while advancements in lesion d…
GPU Semiring Primitives for Sparse Neighborhood Methods
Corey J. Nolet, Divye Gala, Edward Raff +4
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 typ…
A Vector Symbolic Approach to Multiple Instance Learning
Ehsan Ahmed Dhrubo, Mohammad Mahmudul Alam, Edward Raff +2
Multiple Instance Learning (MIL) tasks impose a strict logical constraint: a bag is labeled positive if and only if at least one instance within it is positive. While this iff cons…
Deep Belief Networks used on High Resolution Multichannel Electroencephalography Data for Seizure Detection
JT Turner, Adam Page, Tinoosh Mohsenin +1
Ubiquitous bio-sensing for personalized health monitoring is slowly becoming a reality with the increasing availability of small, diverse, robust, high fidelity sensors. This oncom…
Care-Conditioned Neuromodulation for Autonomy-Preserving Supportive Dialogue Agents
Shalima Binta Manir, Tim Oates
Large language models deployed in supportive or advisory roles must balance helpfulness with preservation of user autonomy, yet standard alignment methods primarily optimize for he…
Hybrid Mortality Prediction using Multiple Source Systems
Isaac Mativo, Yelena Yesha, Michael Grasso +2
The use of artificial intelligence in clinical care to improve decision support systems is increasing. This is not surprising since, by its very nature, the practice of medicine co…
Learning to Segment using Summary Statistics and Weak Supervision
Omkar Kulkarni, Edward Raff, Tim Oates
Medical experts often manually segment images to obtain diagnostic statistics and discard the resulting annotations. We aim to train segmentation models to alleviate this burden, b…
Spatially Encoding Temporal Correlations to Classify Temporal Data Using Convolutional Neural Networks
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. This ena…
Neuroevolution-Based Inverse Reinforcement Learning
Karan K. Budhraja, Tim Oates
The problem of Learning from Demonstration is targeted at learning to perform tasks based on observed examples. One approach to Learning from Demonstration is Inverse Reinforcement…
Towards Generalization in Subitizing with Neuro-Symbolic Loss using Holographic Reduced Representations
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. In p…
DDxT: Deep Generative Transformer Models for Differential Diagnosis
Mohammad Mahmudul Alam, Edward Raff, Tim Oates +1
Differential Diagnosis (DDx) is the process of identifying the most likely medical condition among the possible pathologies through the process of elimination based on evidence. An…
Skin-SOAP: A Weakly Supervised Framework for Generating Structured SOAP Notes
Sadia Kamal, Tim Oates, Joy Wan
Skin carcinoma is the most prevalent form of cancer globally, accounting for over $8 billion in annual healthcare expenditures. Early diagnosis, accurate and timely treatment are c…
Determining the Scale of Impact from Denial-of-Service Attacks in Real Time Using Twitter
Chi Zhang, Bryan Wilkinson, Ashwinkumar Ganesan +1
Denial of Service (DoS) attacks are common in on-line and mobile services such as Twitter, Facebook and banking. As the scale and frequency of Distributed Denial of Service (DDoS)…
The Thing That We Tried Didn't Work Very Well : Deictic Representation in Reinforcement Learning
Sarah Finney, Natalia Gardiol, Leslie Pack Kaelbling +1
Most reinforcement learning methods operate on propositional representations of the world state. Such representations are often intractably large and generalize poorly. Using a dei…
RFC-Net: Learning High Resolution Global Features for Medical Image Segmentation on a Computational Budget
Sourajit Saha, Shaswati Saha, Md Osman Gani +2
Learning High-Resolution representations is essential for semantic segmentation. Convolutional neural network (CNN)architectures with downstream and upstream propagation flow are p…
Extending Signature-based Intrusion Detection Systems WithBayesian Abductive Reasoning
Ashwinkumar Ganesan, Pooja Parameshwarappa, Akshay Peshave +2
Evolving cybersecurity threats are a persistent challenge for systemadministrators and security experts as new malwares are continu-ally released. Attackers may look for vulnerabil…
Graph Node Embeddings using Domain-Aware Biased Random Walks
Sourav Mukherjee, Tim Oates, Ryan Wright
The recent proliferation of publicly available graph-structured data has sparked an interest in machine learning algorithms for graph data. Since most traditional machine learning…
On the use of Deep Autoencoders for Efficient Embedded Reinforcement Learning
Bharat Prakash, Mark Horton, Nicholas R. Waytowich +3
In autonomous embedded systems, it is often vital to reduce the amount of actions taken in the real world and energy required to learn a policy. Training reinforcement learning age…
Learning from Observations Using a Single Video Demonstration and Human Feedback
Sunil Gandhi, Tim Oates, Tinoosh Mohsenin +1
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 vi…
ISM:Self-Improving Strategy Memory for Continual Mathematical Reasoning
Prakhar Dixit, Tim Oates
We propose Intelligent Schema Memory (ISM), a self-evolving memory-augmented system that improves mathematical reasoning for a frozen LLM under continual learning with hard episodi…
Imaging Time-Series to Improve Classification and Imputation
Zhiguang Wang, Tim Oates
Inspired by recent successes of deep learning in computer vision, we propose a novel framework for encoding time series as different types of images, namely, Gramian Angular Summat…
Floorplan2Guide: LLM-Guided Floorplan Parsing for BLV Indoor Navigation
Aydin Ayanzadeh, Tim Oates
Indoor navigation remains a critical challenge for people with visual impairments. The current solutions mainly rely on infrastructure-based systems, which limit their ability to n…
Learning with Holographic Reduced Representations
Ashwinkumar Ganesan, Hang Gao, Sunil Gandhi +4
Holographic Reduced Representations (HRR) are a method for performing symbolic AI on top of real-valued vectors by associating each vector with an abstract concept, and providing m…
Immigration Document Classification and Automated Response Generation
Sourav Mukherjee, Tim Oates, Vince DiMascio +4
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.…
Using Neural Networks for Programming by Demonstration
Karan K. Budhraja, Hang Gao, Tim Oates
Agent-based modeling is a paradigm of modeling dynamic systems of interacting agents that are individually governed by specified behavioral rules. Training a model of such agents t…