research
∙
08/02/2023
Multi-variable Hard Physical Constraints for Climate Model Downscaling
Global Climate Models (GCMs) are the primary tool to simulate climate ev...
share
research
∙
06/09/2023
Hidden symmetries of ReLU networks
The parameter space for any fixed architecture of feedforward ReLU neura...
research
∙
06/07/2023
Normalization Layers Are All That Sharpness-Aware Minimization Needs
Sharpness-aware minimization (SAM) was proposed to reduce sharpness of m...
research
∙
05/23/2023
Fourier Neural Operators for Arbitrary Resolution Climate Data Downscaling
Climate simulations are essential in guiding our understanding of climat...
research
∙
05/01/2023
Bird Distribution Modelling using Remote Sensing and Citizen Science data
Climate change is a major driver of biodiversity loss, changing the geog...
research
∙
04/27/2023
Lightweight, Pre-trained Transformers for Remote Sensing Timeseries
Machine learning algorithms for parsing remote sensing data have a wide ...
research
∙
12/14/2022
Maximal Initial Learning Rates in Deep ReLU Networks
Training a neural network requires choosing a suitable learning rate, in...
research
∙
11/22/2022
PhAST: Physics-Aware, Scalable, and Task-specific GNNs for Accelerated Catalyst Design
Mitigating the climate crisis requires a rapid transition towards lower ...
research
∙
10/24/2022
Understanding the Evolution of Linear Regions in Deep Reinforcement Learning
Policies produced by deep reinforcement learning are typically character...
research
∙
08/24/2022
Bugs in the Data: How ImageNet Misrepresents Biodiversity
ImageNet-1k is a dataset often used for benchmarking machine learning (M...
research
∙
08/08/2022
Generating physically-consistent high-resolution climate data with hard-constrained neural networks
The availability of reliable, high-resolution climate and weather data i...
research
∙
06/09/2022
On Neural Architecture Inductive Biases for Relational Tasks
Current deep learning approaches have shown good in-distribution general...
research
∙
02/04/2022
TIML: Task-Informed Meta-Learning for Agriculture
Labeled datasets for agriculture are extremely spatially imbalanced. Whe...
research
∙
11/29/2021
ClimART: A Benchmark Dataset for Emulating Atmospheric Radiative Transfer in Weather and Climate Models
Numerical simulations of Earth's weather and climate require substantial...
research
∙
06/16/2021
Techniques for Symbol Grounding with SATNet
Many experts argue that the future of artificial intelligence is limited...
research
∙
04/25/2021
DC3: A learning method for optimization with hard constraints
Large optimization problems with hard constraints arise in many settings...
research
∙
02/21/2021
Deep ReLU Networks Preserve Expected Length
Assessing the complexity of functions computed by a neural network helps...
research
∙
10/02/2019
Identifying Weights and Architectures of Unknown ReLU Networks
The output of a neural network depends on its parameters in a highly non...
research
∙
06/10/2019
Tackling Climate Change with Machine Learning
Climate change is one of the greatest challenges facing humanity, and we...
research
∙
06/03/2019
Deep ReLU Networks Have Surprisingly Few Activation Patterns
The success of deep networks has been attributed in part to their expres...
research
∙
01/25/2019
Complexity of Linear Regions in Deep Networks
It is well-known that the expressivity of a neural network depends on it...
research
∙
12/04/2018
Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics
Pixel-accurate tracking of objects is a key element in many computer vis...
research
∙
11/28/2018
Experience Replay for Continual Learning
Continual learning is the problem of learning new tasks or knowledge whi...
research
∙
05/21/2018
Measuring and regularizing networks in function space
Neural network optimization is often conceptualized as optimizing parame...
research
∙
03/05/2018
How to Start Training: The Effect of Initialization and Architecture
We investigate the effects of initialization and architecture on the sta...
research
∙
05/30/2017
Morphological Error Detection in 3D Segmentations
Deep learning algorithms for connectomics rely upon localized classifica...
research
∙
05/30/2017
Deep Learning is Robust to Massive Label Noise
Deep neural networks trained on large supervised datasets have led to im...
research
∙
05/16/2017
The power of deeper networks for expressing natural functions
It is well-known that neural networks are universal approximators, but t...
research
∙
12/07/2016
A Multi-Pass Approach to Large-Scale Connectomics
The field of connectomics faces unprecedented "big data" challenges. To ...
research
∙
08/29/2016
Why does deep and cheap learning work so well?
We show how the success of deep learning could depend not only on mathem...
research
∙
11/19/2015
