Search Results for author:
Found 42 papers, 23 papers with code
Base and Exponent Prediction in Mathematical Expressions using Multi-Output CNN
The use of neural networks and deep learning techniques in image processing has significantly advanced the field, enabling highly accurate recognition results.
Comparing and Contrasting Deep Learning Weather Prediction Backbones on Navier-Stokes and Atmospheric Dynamics
Remarkable progress in the development of Deep Learning Weather Prediction (DLWP) models positions them to become competitive with traditional numerical weather prediction (NWP) models.
IDentity with Locality: An ideal hash for gene sequence search
The standard recipe is to cast the gene search problem as a sequence of membership problems testing if each subsequent gene substring (called kmer) of Q is present in the set of kmers of the entire gene database D. We observe that RH functions, which are crucial to the memory and the computational advantage of BF, are also detrimental to the system performance of gene-search systems.
Collage: Light-Weight Low-Precision Strategy for LLM Training
Large models training is plagued by the intense compute cost and limited hardware memory.
HLAT: High-quality Large Language Model Pre-trained on AWS Trainium
In this paper, we showcase HLAT: a family of 7B and 70B decoder-only LLMs pre-trained using 4096 AWS Trainium accelerators over 1. 8 trillion tokens.
Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning
Integrating and processing information from various sources or modalities are critical for obtaining a comprehensive and accurate perception of the real world in autonomous systems and cyber-physical systems.
Using Uncertainty Quantification to Characterize and Improve Out-of-Domain Learning for PDEs
Existing work in scientific machine learning (SciML) has shown that data-driven learning of solution operators can provide a fast approximate alternative to classical numerical partial differential equation (PDE) solvers.
Neuro-Inspired Hierarchical Multimodal Learning
Integrating and processing information from various sources or modalities are critical for obtaining a comprehensive and accurate perception of the real world.
CAPS: A Practical Partition Index for Filtered Similarity Search
With the surging popularity of approximate near-neighbor search (ANNS), driven by advances in neural representation learning, the ability to serve queries accompanied by a set of constraints has become an area of intense interest.
StyleGAN3: Generative Networks for Improving the Equivariance of Translation and Rotation
StyleGAN can use style to affect facial posture and identity features, and noise to affect hair, wrinkles, skin color and other details.
Theoretical Guarantees of Learning Ensembling Strategies with Applications to Time Series Forecasting
Ensembling is among the most popular tools in machine learning (ML) due to its effectiveness in minimizing variance and thus improving generalization.
Fractional dynamics foster deep learning of COPD stage prediction
The authors show that the fractional dynamic deep learning model (FDDLM) achieves a COPD prediction accuracy of 98. 66% and can serve as a robust alternative to spirometry.
Coupled Multiwavelet Neural Operator Learning for Coupled Partial Differential Equations
Coupled partial differential equations (PDEs) are key tasks in modeling the complex dynamics of many physical processes.
Learning Physical Models that Can Respect Conservation Laws
We provide a detailed analysis of ProbConserv on learning with the Generalized Porous Medium Equation (GPME), a widely-applicable parameterized family of PDEs that illustrates the qualitative properties of both easier and harder PDEs.
Low-Light Image and Video Enhancement: A Comprehensive Survey and Beyond
This paper presents a comprehensive survey of low-light image and video enhancement, addressing two primary challenges in the field.
First De-Trend then Attend: Rethinking Attention for Time-Series Forecasting
Transformer-based models have gained large popularity and demonstrated promising results in long-term time-series forecasting in recent years.
Guiding continuous operator learning through Physics-based boundary constraints
Numerical experiments based on multiple PDEs with a wide variety of applications indicate that the proposed approach ensures satisfaction of BCs, and leads to more accurate solutions over the entire domain.
ProtSi: Prototypical Siamese Network with Data Augmentation for Few-Shot Subjective Answer Evaluation
Subjective answer evaluation is a time-consuming and tedious task, and the quality of the evaluation is heavily influenced by a variety of subjective personal characteristics.
PointNorm: Dual Normalization is All You Need for Point Cloud Analysis
Point cloud analysis is challenging due to the irregularity of the point cloud data structure.
AS-IntroVAE: Adversarial Similarity Distance Makes Robust IntroVAE
However, due to the unavailability of an effective metric to evaluate the difference between the real and the fake images, the posterior collapse and the vanishing gradient problem still exist, reducing the fidelity of the synthesized images.
Functional Optimization Reinforcement Learning for Real-Time Bidding
In order to evaluate the proposed RTB strategy's performance, we demonstrate the results on ten sequential simulated auction campaigns.
Secure Distributed/Federated Learning: Prediction-Privacy Trade-Off for Multi-Agent System
Decentralized learning is an efficient emerging paradigm for boosting the computing capability of multiple bounded computing agents.
Unsupervised Domain Adaptation for Cardiac Segmentation: Towards Structure Mutual Information Maximization
This paper introduces UDA-VAE++, an unsupervised domain adaptation framework for cardiac segmentation with a compact loss function lower bound.
SAPNet: Segmentation-Aware Progressive Network for Perceptual Contrastive Deraining
To address this issue, in this paper, we present a segmentation-aware progressive network (SAPNet) based upon contrastive learning for single image deraining.
Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancement
Firstly, we design an enhancement factor extraction network using depthwise separable convolution for an efficient estimate of the pixel-wise light deficiency of an low-light image.
STORM: Sketch Toward Online Risk Minimization
To this end, we propose STORM, an online sketching-based method for empirical risk minimization.
Non-Linear Operator Approximations for Initial Value Problems
The Padé exponential operator uses a $\textit{recurrent structure with shared parameters}$ to model the non-linearity compared to recent neural operators that rely on using multiple linear operator layers in succession.
Multiwavelet-based Operator Learning for Differential Equations
The solution of a partial differential equation can be obtained by computing the inverse operator map between the input and the solution space.
Non-Markovian Reinforcement Learning using Fractional Dynamics
Reinforcement learning (RL) is a technique to learn the control policy for an agent that interacts with a stochastic environment.
IRLI: Iterative Re-partitioning for Learning to Index
Neural models have transformed the fundamental information retrieval problem of mapping a query to a giant set of items.
STORM: Foundations of End-to-End Empirical Risk Minimization on the Edge
To this end, we propose STORM, an online sketch for empirical risk minimization.
Fast Processing and Querying of 170TB of Genomics Data via a Repeated And Merged BloOm Filter (RAMBO)
Interestingly, it is a count-min sketch type arrangement of a membership testing utility (Bloom Filter in our case).
RAMBO: Repeated And Merged Bloom Filter for Multiple Set Membership Testing (MSMT) in Sub-linear time
A simple array of Bloom Filters can achieve that.
Noisy Batch Active Learning with Deterministic Annealing
We study the problem of training machine learning models incrementally with batches of samples annotated with noisy oracles.
Learning in Confusion: Batch Active Learning with Noisy Oracle
We study the problem of training machine learning models incrementally using active learning with access to imperfect or noisy oracles.
Learning Information Propagation in the Dynamical Systems via Information Bottleneck Hierarchy
Extracting relevant information, causally inferring and predicting the future states with high accuracy is a crucial task for modeling complex systems.
Data-driven Perception of Neuron Point Process with Unknown Unknowns
Previous research of neuron activity analysis is mainly limited with effects from the spiking history of target neuron and the interaction with other neurons in the system while ignoring the influence of unknown stimuli.
Learning Latent Fractional dynamics with Unknown Unknowns
Despite significant effort in understanding complex systems (CS), we lack a theory for modeling, inference, analysis and efficient control of time-varying complex networks (TVCNs) in uncertain environments.
Approximate Submodular Functions and Performance Guarantees
Nonetheless, often we leverage the greedy algorithms used in submodular functions to determine a solution to the non-submodular functions.
Anonymizing k-Facial Attributes via Adversarial Perturbations
A face image not only provides details about the identity of a subject but also reveals several attributes such as gender, race, sexual orientation, and age.
Dealing with Unknown Unknowns: Identification and Selection of Minimal Sensing for Fractional Dynamics with Unknown Inputs
This paper focuses on analysis and design of time-varying complex networks having fractional order dynamics.
Passive Classification of Source Printer using Text-line-level Geometric Distortion Signatures from Scanned Images of Printed Documents
This paper proposes a set of features for characterizing text-line-level geometric distortions, referred as geometric distortion signatures and presents a novel system to use them for identification of the origin of a printed document.
