Related papers: Interpretable Multimodal Machine Learning Analysis…
Simulation of spectra of x-ray absorption spectroscopy (XAS) at the L-edge is a well-established and reliable computational tool that, in combination with experimental measurements, reveals details about the local electronic structure and…
We present a reciprocal-space pseudopotential scheme for calculating X-ray absorption near-edge structure (XANES) spectra. The scheme incorporates a recursive method to compute absorption cross section as a continued fraction. The continued…
Materials science datasets are inherently heterogeneous and are available in different modalities such as characterization spectra, atomic structures, microscopic images, and text-based synthesis conditions. The advancements in multi-modal…
Given Spatial Variability Aware Neural Networks (SVANNs), the goal is to investigate mathematical (or computational) models for comparative physical interpretation towards their transparency (e.g., simulatibility, decomposability and…
This paper describes methods for comparative evaluation of the interpretability of models of high dimensional time series data inferred by unsupervised machine learning algorithms. The time series data used in this investigation were logs…
We consider probabilistic topic models and more recent word embedding techniques from a perspective of learning hidden semantic representations. Inspired by a striking similarity of the two approaches, we merge them and learn probabilistic…
Autoencoders are powerful machine learning models used to compress information from multiple data sources. However, autoencoders, like all artificial neural networks, are often unidentifiable and uninterpretable. This research focuses on…
Sparse autoencoders (SAEs) have shown promise in extracting interpretable features from complex neural networks. We present one of the first applications of SAEs to dense text embeddings from large language models, demonstrating their…
While machine learning techniques have been successfully applied in several fields, the black-box nature of the models presents challenges for interpreting and explaining the results. We develop a new framework called Adaptive Explainable…
Live-cell imaging of multiple subcellular structures is essential for understanding subcellular dynamics. However, the conventional multi-color sequential fluorescence microscopy suffers from significant imaging delays and limited number of…
This paper provides a brief overview of applications of advanced X-ray spectroscopic techniques that take advantage of the resonant inelastic X-ray scattering (RIXS) in the hard and tender x-ray range and have recently become available for…
We introduce scalable machine learning models to accurately predict two key quantum transport properties, the transmission coefficient T(E) and average local density of states (Average-LDOS) in two-dimensional (2D) hexagonal materials with…
Model interpretability is an increasingly important component of practical machine learning. Some of the most common forms of interpretability systems are example-based, local, and global explanations. One of the main challenges in…
Recent advances in materials discovery have been driven by structure-based models, particularly those using crystal graphs. While effective for computational datasets, these models are impractical for real-world applications where atomic…
Sparse autoencoders (SAEs) have proven useful in disentangling the opaque activations of neural networks, primarily large language models, into sets of interpretable features. However, adapting them to domains beyond language, such as…
Decision-making in complex systems often relies on machine learning models, yet highly accurate models such as XGBoost and neural networks can obscure the reasoning behind their predictions. In operations research applications,…
While the uptake of data-driven approaches for materials science and chemistry is at an exciting, early stage, to realise the true potential of machine learning models for successful scientific discovery, they must have qualities beyond…
Interpretability is a pressing issue for machine learning. Common approaches to interpretable machine learning constrain interactions between features of the input, rendering the effects of those features on a model's output comprehensible…
Advanced machine learning models have recently achieved high predictive accuracy for weather and climate prediction. However, these complex models often lack inherent transparency and interpretability, acting as "black boxes" that impede…
Deep neural networks have been widely used in text classification. However, it is hard to interpret the neural models due to the complicate mechanisms. In this work, we study the interpretability of a variant of the typical text…