Results 71 to 80 of about 6,466,948 (249)
Metal‐free carbon catalysts enable the sustainable synthesis of hydrogen peroxide via two‐electron oxygen reduction; however, active site complexity continues to hinder reliable interpretation. This review critiques correlation‐based approaches and highlights the importance of orthogonal experimental designs, standardized catalyst passports ...
Dayu Zhu +3 more
wiley +1 more source
Functional Variational Bayesian Neural Networks
ICLR ...
Shengyang Sun +3 more
openaire +4 more sources
Bayesian Neural Networks: An Introduction and Survey [PDF]
Neural Networks (NNs) have provided state-of-the-art results for many challenging machine learning tasks such as detection, regression and classification across the domains of computer vision, speech recognition and natural language processing. Despite their success, they are often implemented in a frequentist scheme, meaning they are unable to reason ...
Goan, Ethan, Fookes, Clinton
openaire +3 more sources
Flat Seeking Bayesian Neural Networks
Bayesian Neural Networks (BNNs) provide a probabilistic interpretation for deep learning models by imposing a prior distribution over model parameters and inferring a posterior distribution based on observed data. The model sampled from the posterior distribution can be used for providing ensemble predictions and quantifying prediction uncertainty.
Van-Anh Nguyen +5 more
openaire +4 more sources
This review highlights the role of self‐assembled monolayers (SAMs) in perovskite solar cells, covering molecular engineering, multifunctional interface regulation, machine learning (ML) accelerated discovery, advanced device architectures, and pathways toward scalable fabrication and commercialization for high‐efficiency and stable single‐junction and
Asmat Ullah, Ying Luo, Stefaan De Wolf
wiley +1 more source
Singular Bayesian Neural Networks
Bayesian neural networks promise calibrated uncertainty but require $O(mn)$ parameters for standard mean-field Gaussian posteriors. We argue this cost is often unnecessary, particularly when weight matrices exhibit fast singular value decay. By parameterizing weights as $W = AB^{\top}$ with $A \in \mathbb{R}^{m \times r}$, $B \in \mathbb{R}^{n \times r}
Mame Diarra Toure, David A. Stephens
openaire +3 more sources
Variational Laplace for Bayesian neural networks
We develop variational Laplace for Bayesian neural networks (BNNs) which exploits a local approximation of the curvature of the likelihood to estimate the ELBO without the need for stochastic sampling of the neural-network weights. The Variational Laplace objective is simple to evaluate, as it is (in essence) the log-likelihood, plus weight-decay, plus
Unlu, Ali, Aitchison, Laurence
openaire +4 more sources
Improved Uncertainty Quantification for Neural Networks With Bayesian Last Layer
Uncertainty quantification is an important task in machine learning - a task in which standard neural networks (NNs) have traditionally not excelled. This can be a limitation for safety-critical applications, where uncertainty-aware methods like Gaussian
Felix Fiedler, Sergio Lucia
doaj +1 more source
The perspective presents an integrated view of neuromorphic technologies, from device physics to real‐time applicability, while highlighting the necessity of full‐stack co‐optimization. By outlining practical hardware‐level strategies to exploit device behavior and mitigate non‐idealities, it shows pathways for building efficient, scalable, and ...
Kapil Bhardwaj +8 more
wiley +1 more source
Organic Materials of Tomorrow: Horizons of Artificial Intelligence
This review examines machine learning techniques accelerating the discovery of organic semiconductors by linking molecular structure to properties. Key methods include graph neural networks, generative models, and active learning. Applications to organic photovoltaics demonstrate practical impact.
Harold Mena +3 more
wiley +1 more source

