26 papers · ranked by Valyu relevance
Corrado Pancotti, Piero Fariselli, Jonas Meisner, Anders Krogh
In this paper, we demonstrate that it is feasible to train a deep generative model for dimensionality reduction with millions of features using few samples, which makes this type of generative model a more versatile alternative to standard methods for dimensionality reduction. Specifically, we hypothesize that for a…
Moustafa Alzantot, Luis García, Mani Srivastava
Generative models such as the variational autoencoder (VAE) and the generative adversarial networks (GAN) have proven to be incredibly powerful for the generation of synthetic data that preserves statistical properties and utility of realworld datasets, especially in the context of image and natural language text.…
Reinhard Heckel, Paul Hand
Deep neural networks, in particular convolutional neural networks, have become highly effective tools for compressing images and solving inverse problems including denoising, inpainting, and reconstruction from few and noisy measurements. This success can be attributed in part to their ability to represent and generate…
Yuhuai Wu, Yuri Burda, Ruslan Salakhutdinov, Roger Grosse
The past several years have seen remarkable progress in generative models which produce convincing samples of images and other modalities. A shared component of many powerful generative models is a decoder network, a parametric deep neural net that defines a generative distribution. Examples include variational…
Mengran Yan, Chun Tang, Jida Yan, Siti Suhaily Surip + 1 more
Pattern design is essential in various domains, especially in traditional lantern production, where patterns convey cultural history and artistic values. Our research presents an innovative generative model that produces customizable lantern patterns, integrating classical aesthetics with modern design features via a…
Guoqiang Zhong, Wei Gao, Yongbin Liu, Youzhao Yang
—In recent years, research on image generation methods has been developing fast. The auto-encoding variational Bayes method (VAEs) was proposed in 2013, which uses variational inference to learn a latent space from the image database and then generates images using the decoder. The generative adversarial networks…
Xuezhe Ma, Xiang Kong, Shanghang Zhang, Eduard Hovy
In this work, we propose a new generative model that is capable of automatically decoupling global and local representations of images in an entirely unsupervised setting, by embedding a generative flow in the VAE framework to model the decoder. Specifically, the proposed model utilizes the variational auto-encoding…
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…
Aghiles Kebaili, Jérôme Lapuyade-Lahorgue, Su Ruan, Cecilia Di Ruberto + 4 more
Deep learning has become a popular tool for medical image analysis, but the limited availability of training data remains a major challenge, particularly in the medical field where data acquisition can be costly and subject to privacy regulations. Data augmentation techniques offer a solution by artificially increasing…
Brandon Wong, Brokoslaw Laschowski
Neural decoding can be viewed as a representation learning problem in which neural activity is mapped into an intermediate representation before downstream reconstruction. The choice of intermediate representation influences both performance and learning difficulty. Here we developed a novel framework for studying how…
Victor H. R. Nogueira, Rishabh Sharma, Rafael V. C. Guido, Michael J. Keiser
As efforts to improve the robustness of molecular representations advance, so does the need for methods to test and validate them. We use a Variational Auto-Encoder (VAE), an unsupervised deep learning model, to generate anomalous samples of a well-known molecular string format called SELF-referencIng Embedded Strings…
Minjoo Kim, Yelim Kim, Won Il Park
This study introduces an optical neural network (ONN)-based autoencoder for efficient image processing, utilizing specialized optical matrix-vector multipliers for both encoding and decoding tasks. To address the challenges in efficient decoding, we propose a method that optimizes output processing through scalar…
Aman Singh, Tokunbo Ogunfunmi, Sotiris Kotsiantis
Autoencoders are a self-supervised learning system where, during training, the output is an approximation of the input. Typically, autoencoders have three parts: Encoder (which produces a compressed latent space representation of the input data), the Latent Space (which retains the knowledge in the input data with…
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…
Kuan Han, Haiguang Wen, Junxing Shi, Kun-Han Lu + 2 more
Goal-driven and feedforward-only convolutional neural networks (CNN) have been shown to be able to predict and decode cortical responses to natural images or videos. Here, we explored an alternative deep neural network, variational auto-encoder (VAE), as a computational model of the visual cortex. We trained a VAE with…
Vignesh Sampath, Iñaki Maurtua, Juan José Aguilar Martín, Aitor Gutierrez
Any computer vision application development starts off by acquiring images and data, then preprocessing and pattern recognition steps to perform a task. When the acquired images are highly imbalanced and not adequate, the desired task may not be achievable. Unfortunately, the occurrence of imbalance problems in…
Tianyang Hu, Fei Chen, Haonan Wang, Jiawei Li + 3 more
'Jiacheng Sun' 'Zhenguo Li'] In generative modeling, numerous successful approaches leverage a lowdimensional latent space, e.g., Stable Diffusion [68] models the latent space induced by an encoder and generates images through a paired decoder. Although the selection of the latent space is empirically pivotal…
Benchen Yang, Xuzhao Liu, Yize Li, Haibo Jin + 2 more
Unpaired image-to-image translation (I2IT) involves establishing an effective mapping between the source and target domains to enable cross-domain image transformation. Previous contrastive learning methods inadequately accounted for the variations in features between two domains and the interrelatedness of elements…
Yuling He, Yingding Zhao, Wenji Yang, Yilu Xu + 1 more
'Juan Pedro Dominguez-Morales'] Due to the sophisticated entanglements for non-rigid deformation, generating person images from source pose to target pose is a challenging work. In this paper, we present a novel framework to generate person images with shape consistency and appearance consistency. The proposed…
Florian Eichin, Maren Hackenberg, Caroline Broichhagen, Antje Kilias + 3 more
Live imaging techniques, such as two-photon imaging, promise novel insights into cellular activity patterns at a high spatial and temporal resolution. While current deep learning approaches typically focus on specific supervised tasks in the analysis of such data, e.g., learning a segmentation mask as a basis for…
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…
Kiran Bacsa, Zhilu Lai, Wei Liu, Michael Todd + 1 more
We propose a new variational autoencoder (VAE) with physical constraints capable of learning the dynamics of Multiple Degree of Freedom (MDOF) dynamic systems. Standard variational autoencoders place greater emphasis on compression than interpretability regarding the learned latent space. We propose a new type of…
Authors not listed
Deep generative models are transforming early-stage drug discovery, yet most current approaches are not well suited for realistic, small-data settings and often rely on simplified molecular representations such as linear strings, overlooking the inherent graph-based structure of molecules. To address this, we first…
Authors not listed
In recent years, generative deep learning has emerged as a transformative approach in drug design, promising to explore the vast chemical space and generate novel molecules with desired biological properties. This perspective examines the challenges and opportunities of applying generative models to drug discovery…
Jie Lin, Mingyuan Xu, Hongming Chen
Shape-based virtual screening is a widely utilized method in ligand-based de novo drug design, aiming to identify molecules in chemical libraries that share similar 3D shapes but simultaneously possess novel 2D chemical structures compared to the reference compound. As an emerging technology, generative model is an…
Wout Bittremieux, Varun Ananth, William E. Fondrie, Carlo Melendez + 5 more
Protein tandem mass spectrometry data is most often interpreted by matching observed mass spectra to a protein database derived from the reference genome of the sample being analyzed. In many application domains, however, a relevant protein database is unavailable or incomplete, and in such settings de novo sequencing…