[HTML][HTML] A survey of topological machine learning methods

F Hensel, M Moor, B Rieck - Frontiers in Artificial Intelligence, 2021 - frontiersin.org
The last decade saw an enormous boost in the field of computational topology: methods and
concepts from algebraic and differential topology, formerly confined to the realm of pure …

[HTML][HTML] Computer-aided multi-objective optimization in small molecule discovery

JC Fromer, CW Coley - Patterns, 2023 - cell.com
Molecular discovery is a multi-objective optimization problem that requires identifying a
molecule or set of molecules that balance multiple, often competing, properties. Multi …

Neural fields in visual computing and beyond

Y Xie, T Takikawa, S Saito, O Litany… - Computer Graphics …, 2022 - Wiley Online Library
Recent advances in machine learning have led to increased interest in solving visual
computing problems using methods that employ coordinate‐based neural networks. These …

[HTML][HTML] PoseBusters: AI-based docking methods fail to generate physically valid poses or generalise to novel sequences

M Buttenschoen, GM Morris, CM Deane - Chemical Science, 2024 - pubs.rsc.org
The last few years have seen the development of numerous deep learning-based protein–
ligand docking methods. They offer huge promise in terms of speed and accuracy. However …

The landscape of tolerated genetic variation in humans and primates

H Gao, T Hamp, J Ede, JG Schraiber, J McRae… - Science, 2023 - science.org
Personalized genome sequencing has revealed millions of genetic differences between
individuals, but our understanding of their clinical relevance remains largely incomplete. To …

Exploring deep neural networks via layer-peeled model: Minority collapse in imbalanced training

C Fang, H He, Q Long, WJ Su - Proceedings of the National …, 2021 - National Acad Sciences
In this paper, we introduce the Layer-Peeled Model, a nonconvex, yet analytically tractable,
optimization program, in a quest to better understand deep neural networks that are trained …

High-dimensional limit theorems for sgd: Effective dynamics and critical scaling

G Ben Arous, R Gheissari… - Advances in Neural …, 2022 - proceedings.neurips.cc
We study the scaling limits of stochastic gradient descent (SGD) with constant step-size in
the high-dimensional regime. We prove limit theorems for the trajectories of summary …

State‐of‐the‐Art in the Architecture, Methods and Applications of StyleGAN

AH Bermano, R Gal, Y Alaluf, R Mokady… - Computer Graphics …, 2022 - Wiley Online Library
Abstract Generative Adversarial Networks (GANs) have established themselves as a
prevalent approach to image synthesis. Of these, StyleGAN offers a fascinating case study …

Detection and classification of cancer in whole slide breast histopathology images using deep convolutional networks

B Gecer, S Aksoy, E Mercan, LG Shapiro, DL Weaver… - Pattern recognition, 2018 - Elsevier
Generalizability of algorithms for binary cancer vs. no cancer classification is unknown for
clinically more significant multi-class scenarios where intermediate categories have different …

[HTML][HTML] Scaffold-based molecular design with a graph generative model

J Lim, SY Hwang, S Moon, S Kim, WY Kim - Chemical science, 2020 - pubs.rsc.org
Searching for new molecules in areas like drug discovery often starts from the core
structures of known molecules. Such a method has called for a strategy of designing …