Related papers: A Mass-Conserving-Perceptron for Machine Learning-…

The efficient coding hypothesis proposes that the response properties of sensory systems are adapted to the statistics of their inputs such that they capture maximal information about the environment, subject to biological constraints.…

Extreme ocean phenomena are challenging not only to predict but to diagnose, as accurate forecasts alone do not reveal the underlying physical drivers. While recent machine learning approaches achieve strong predictive skill, they remain…

In recent years, Graph Convolutional Networks (GCNs) have been widely used in human motion prediction, but their performance remains unsatisfactory. Recently, MLP-Mixer, initially developed for vision tasks, has been leveraged into human…

Generative artificial intelligence (AI) has made unprecedented advances in vision language models over the past two years. During the generative process, new samples (images) are generated from an unknown high-dimensional distribution.…

Pre-trained on extensive text and image corpora, current Multi-Modal Large Language Models (MLLM) have shown strong capabilities in general visual reasoning tasks. However, their performance is still lacking in physical domains that require…

In recent years, the geospatial industry has been developing at a steady pace. This growth implies the addition of satellite constellations that produce a copious supply of satellite imagery and other Remote Sensing data on a daily basis.…

Multi-channel time-series data, prevalent across diverse applications, is characterized by significant heterogeneity in its different channels. However, existing forecasting models are typically guided by channel-agnostic loss functions…

We present a new adaptation method MaCP, Minimal yet Mighty adaptive Cosine Projection, that achieves exceptional performance while requiring minimal parameters and memory for fine-tuning large foundation models. Its general idea is to…

We present a new adaptation method MaCP, Minimal yet Mighty adaptive Cosine Projection, that achieves exceptional performance while requiring minimal parameters and memory for fine-tuning large foundation models. Its general idea is to…

Model Predictive Control (MPC) has become a popular framework in embedded control for high-performance autonomous systems. However, to achieve good control performance using MPC, an accurate dynamics model is key. To maintain real-time…

Multivariate time series forecasting is an important yet challenging problem in machine learning. Most existing approaches only forecast the series value of one future moment, ignoring the interactions between predictions of future moments…

Building accurate and interpretable Machine Learning (ML) models for heterogeneous/mixed data is a long-standing challenge for algorithms designed for numeric data. This work focuses on developing numeric coding schemes for non-numeric…

Rapid progress in the field of machine-learning for weather prediction has led to the emergence of algorithms whose forecasting skill can exceed that of traditional physically based models. This development represents an opportunity to…

We propose an algorithm grounded in dynamical systems theory that generalizes manifold learning from a global state representation, to a network of local interacting manifolds termed a Generative Manifold Network (GMN). Manifolds are…

In this study, we present a sophisticated hybrid machine-learning framework that significantly improves the accuracy of predicting hydrogen storage capacities in metal hydrides. This is a critical challenge due to the scarcity of…

Accurate cyclone forecasting is essential for minimizing loss of life, infrastructure damage, and economic disruption. Traditional numerical weather prediction models, though effective, are computationally intensive and prone to error due…

The electric grid is a key enabling infrastructure for the ambitious transition towards carbon neutrality as we grapple with climate change. With deepening penetration of renewable energy resources and electrified transportation, the…

Maximum Manifold Capacity Representations (MMCR) is a recent multi-view self-supervised learning (MVSSL) method that matches or surpasses other leading MVSSL methods. MMCR is intriguing because it does not fit neatly into any of the…

A Hyperspectral image contains much more number of channels as compared to a RGB image, hence containing more information about entities within the image. The convolutional neural network (CNN) and the Multi-Layer Perceptron (MLP) have been…

Success of machine learning (ML) in the modern world is largely determined by abundance of data. However at many industrial and scientific problems, amount of data is limited. Application of ML methods to data-scarce scientific problems can…