Position paper: Bayesian deep learning in the age of large-scale ai
In the current landscape of deep learning research, there is a predominant emphasis on
achieving high predictive accuracy in supervised tasks involving large image and language …
achieving high predictive accuracy in supervised tasks involving large image and language …
Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI
In the current landscape of deep learning research, there is a predominant emphasis on
achieving high predictive accuracy in supervised tasks involving large image and language …
achieving high predictive accuracy in supervised tasks involving large image and language …
Empowering approximate Bayesian neural networks with functional priors through anchored ensembling for mechanics surrogate modeling applications
In recent years, neural networks (NNs) have become increasingly popular for surrogate
modeling tasks in mechanics and materials modeling applications. While traditional NNs are …
modeling tasks in mechanics and materials modeling applications. While traditional NNs are …
Finetuning CLIP to Reason about Pairwise Differences
Vision-language models (VLMs) such as CLIP are trained via contrastive learning between
text and image pairs, resulting in aligned image and text embeddings that are useful for …
text and image pairs, resulting in aligned image and text embeddings that are useful for …
Empowering Bayesian Neural Networks with Functional Priors through Anchored Ensembling for Mechanics Surrogate Modeling Applications
J Ghorbanian, N Casaprima, A Olivier - arXiv preprint arXiv:2409.05234, 2024 - arxiv.org
In recent years, neural networks (NNs) have become increasingly popular for surrogate
modeling tasks in mechanics and materials modeling applications. While traditional NNs are …
modeling tasks in mechanics and materials modeling applications. While traditional NNs are …
Towards Physically Interpretable World Models: Meaningful Weakly Supervised Representations for Visual Trajectory Prediction
Z Mao, I Ruchkin - arXiv preprint arXiv:2412.12870, 2024 - arxiv.org
Deep learning models are increasingly employed for perception, prediction, and control in
complex systems. Embedding physical knowledge into these models is crucial for achieving …
complex systems. Embedding physical knowledge into these models is crucial for achieving …
Optimization Proxies using Limited Labeled Data and Training Time--A Semi-Supervised Bayesian Neural Network Approach
Constrained optimization problems arise in various engineering system operations such as
inventory management and electric power grids. However, the requirement to repeatedly …
inventory management and electric power grids. However, the requirement to repeatedly …
Bayesian Entropy Neural Networks for Physics-Aware Prediction
This paper addresses the need for deep learning models to integrate well-defined
constraints into their outputs, driven by their application in surrogate models, learning with …
constraints into their outputs, driven by their application in surrogate models, learning with …