26 papers · ranked by Valyu relevance
Jakub M. Tomczak
There are multiple classes of (deep) generative models, namely, mixture models, Probabilistic Circuits, Autoregressive Models (and their special example, Large Language Models), Flow-based Models, Latent Variable Models, GANs, Hybrid (or Joint) Models, Score-based Generative Models, Diffusion-based Models, and…
Jens Nußberger, Frederic Boesel, Stefan Lenz, Harald Binder + 1 more
Deep generative models can be trained to represent the joint distribution of data, such as measurements of single nucleotide polymorphisms (SNPs) from several individuals. Subsequently, synthetic observations are obtained by drawing from this distribution. This has been shown to be useful for several tasks, such as…
Martin Treppner, Harald Binder, Moritz Hess
Deep generative models can learn the underlying structure, such as pathways or gene programs, from omics data. We provide an introduction as well as an overview of such techniques, specifically illustrating their use with single-cell gene expression data. For example, the low dimensional latent representations offered…
Stefan Lenz, Moritz Hess, Harald Binder
Background The best way to calculate statistics from medical data is to use the data of individual patients. In some settings, this data is difficult to obtain due to privacy restrictions. In Germany, for example, it is not possible to pool routine data from different hospitals for research purposes without the consent…
Zhiting Hu, Zichao Yang, Ruslan Salakhutdinov, Eric P. Xing
Deep generative models have achieved impressive success in recent years. Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), as emerging families for generative model learning, have largely been considered as two distinct paradigms and received extensive independent studies respectively. This…
Stefan Lenz, Harald Binder
The best way to calculate statistics from medical data is to use the data of individual patients. In some settings, this data is difficult to obtain due to privacy restrictions. In Germany, for example, it is not possible to pool routine data from different hospitals for research purposes without the consent of the…
Danilo Jimenez Rezende, Shakir Mohamed, Ivo Danihelka, Karol Gregor + 1 more
'Daan Wierstra'] Humans have an impressive ability to reason about new concepts and experiences from just a single example. In particular, humans have an ability for one-shot generalization: an ability to encounter a new concept, understand its structure, and then be able to generate compelling alternative variations…
Ambuj Tewari
Beginning with text and images, generative AI has expanded to audio, video, computer code, and molecules. Yet, if generative AI is the answer, what is the question? We explore the foundations of generation as a distinct machine learning task with connections to prediction, compression, and decision-making. We survey…
Romain Lopez, Adam Gayoso, Nir Yosef
Generative models provide a well-established statistical framework for evaluating uncertainty and deriving conclusions from large data sets especially in the presence of noise, sparsity, and bias. Initially developed for computer vision and natural language processing, these models have been shown to effectively…
Nathan Mancheun Lui, Max D Li, Matthew Ford
Deep generative models for molecular graphs offer a new avenue for property optimization in drug discovery. Optimizing differentiable models that generate molecular graphs is certainly faster, cheaper, and much more accessible than traditional methods of chemical synthesis. Recent advances in generative modeling have…
André Bauer, Simon Trapp, Michael Stenger, Robert Leppich + 4 more
'Samuel Kounev' 'Mark Leznik' 'Kyle Chard' 'Ian Foster'] Recent years have witnessed a surge in the popularity of Machine Learning (ML), applied across diverse domains. However, progress is impeded by the scarcity of training data due to expensive acquisition and privacy legislation. Synthetic data emerges as a…
Sihan Xie, Thierry Tribout, Didier Boichard, Blaise Hanczar + 2 more
Deep generative models open new avenues for simulating realistic genomic data while preserving privacy and addressing data accessibility constraints. While previous studies have primarily focused on generating gene expression or haplotype data, this study explores generating genotype data in both unconditioned and…
Marco Zorzi, Alberto Testolin, Ivilin P. Stoianov
Deep unsupervised learning in stochastic recurrent neural networks with many layers of hidden units is a recent breakthrough in neural computation research. These networks build a hierarchy of progressively more complex distributed representations of the sensory data by fitting a hierarchical generative model. In this…
Siqi Nie, Meng Zheng, Qiang Ji
Deep directed generative models have attracted much attention recently due to their generative modeling nature and powerful data representation ability. In this paper, we review different structures of deep directed generative models and the learning and inference algorithms associated with the structures. We focus on…
Samuel Renaud, Rachael Mansbach
Current antibacterial treatments cannot overcome the rapidly growing resistance of bacteria to antibiotic drugs, and novel treatment methods are required. One option is the development of new antimicrobial peptides (AMPs), to which bacterial resistance build-up is comparatively slow. Deep generative models have…
Zineb Sordo, Eric Chagnon, Zixi Hu, Jeffrey J. Donatelli + 6 more
'Peter Andeer' 'Peter S. Nico' 'Trent Northen' 'Daniela Ushizima' 'Raimondo Schettini' 'Guanghui (Richard) Wang'] Generative AI (genAI) has emerged as a powerful tool for synthesizing diverse and complex image data, offering new possibilities for scientific imaging applications. This review presents a comprehensive…
Josep Arús-Pous, Thomas Blaschke, Silas Ulander, Jean-Louis Reymond + 2 more
Recent applications of Recurrent Neural Networks enable training models that sample the chemical space. In this study we train RNN with molecular string representations (SMILES) with a subset of the enumerated database GDB-13 (975 million molecules). We show that a model trained with 1 million structures (0.1 % of the…
Josep Arús-Pous, Thomas Blaschke, Jean-Louis Reymond, Hongming Chen + 1 more
Recent applications of Recurrent Neural Networks enable training models that sample the chemical space. In this study we train RNN with molecular string representations (SMILES) with a subset of the enumerated database GDB-13 (975 million molecules). We show that a model trained with 1 million structures (0.1 % of the…
Burak Yelmen, Aurélien Decelle, Linda Ongaro, Davide Marnetto + 5 more
Generative models have shown breakthroughs in a wide spectrum of domains due to recent advancements in machine learning algorithms and increased computational power. Despite these impressive achievements, the ability of generative models to create realistic synthetic data is still under-exploited in genetics and absent…
Chensi Cao, Feng Liu, Hai Tan, Deshou Song + 5 more
'Weizhong Li' 'Yiming Zhou' 'Xiaochen Bo' 'Zhi Xie'] Advances in biological and medical technologies have been providing us explosive volumes of biological and physiological data, such as medical images, electroencephalography, genomic and protein sequences. Learning from these data facilitates the understanding of…
Philipp Renz, Dries Van Rompaey, Jörg Kurt Wegner, Sepp Hochreiter + 1 more
There has been a wave of generative models for molecules triggered by advances in the field of Deep Learning. These generative models are often used to optimize chemical compounds towards particular properties or a desired biological activity. The evaluation of generative models remains challenging and suggested…
Travers Ching, Daniel S. Himmelstein, Brett K. Beaulieu-Jones, Alexandr A. Kalinin + 23 more
Deep learning, which describes a class of machine learning algorithms, has recently showed impressive results across a variety of domains. Biology and medicine are data rich, but the data are complex and often ill-understood. Problems of this nature may be particularly well-suited to deep learning techniques. We…
Ghislain St-Yves, Thomas Naselaris
We consider the inference problem of reconstructing a visual stimulus from brain activity measurements (e.g. fMRI) that encode this stimulus. Recovering a complete image is complicated by the fact that neural representations are noisy, high-dimensional, and contain incomplete information about image details. Thus…
Alex Lamb
One of the most distinctive and powerful aspects of human cognition is the ability to imagine: to synthesize mental objects which are not bound by what is immediately present in reality. There are many potential reasons why humans evolved this capability. One is that it allows humans to do planning by imagining how…
Authors not listed
Solving optimization problems, especially for nonlinear and constrained systems, is a challenge. Decades of specialized algorithms have been developed for general and special cases of root finding, minimization (including constraints), for parameter estimation, and mapping connected spaces. These approaches typically…
David Buterez, Jon Paul Janet, Steven Kiddle, Pietro Liò
We investigate the potential of graph neural networks for transfer learning and improving molecular property prediction on sparse and expensive to acquire high-fidelity data by leveraging low-fidelity measurements as an inexpensive proxy for a targeted property ofinterest. This problem arises in discovery processes…