AI models collapse when trained on recursively generated data by Shumailov, I, Shumaylov, Z, Zhao, Y, Papernot, N, Anderson, R, Gal, Y

“…We refer to this effect as ‘model collapse’ and show that it can occur in LLMs as well as in variational autoencoders (VAEs) and Gaussian mixture models (GMMs). …”

Neural network flows of low q-state Potts and clock models by Dimitrios Giataganas, Ching-Yu Huang, Feng-Li Lin

“…Here we construct a variety of neural network (NN) flows using the RBM and (variational) autoencoders, to study the q -state Potts and clock models on the square lattice for q = 2, 3, 4. …”
Get full text

Imputation of label-free quantitative mass spectrometry-based proteomics data using self-supervised deep learning by Henry Webel, Lili Niu, Annelaura Bach Nielsen, Marie Locard-Paulet, Matthias Mann, Lars Juhl Jensen, Simon Rasmussen

“…Here we demonstrate how collaborative filtering, denoising autoencoders, and variational autoencoders can impute missing values in the context of LFQ at different levels. …”
Get full text

Identification of transcriptional programs using dense vector representations defined by mutual information with GeneVector by Nicholas Ceglia, Zachary Sethna, Samuel S. Freeman, Florian Uhlitz, Viktoria Bojilova, Nicole Rusk, Bharat Burman, Andrew Chow, Sohrab Salehi, Farhia Kabeer, Samuel Aparicio, Benjamin D. Greenbaum, Sohrab P. Shah, Andrew McPherson

“…Unlike other methods, including principal component analysis and variational autoencoders, GeneVector uses latent space arithmetic in a lower dimensional gene embedding to identify transcriptional programs and classify cell types. …”
Get full text

Data-driven multi-objective molecular design of ionic liquid with high generation efficiency on small dataset by Xiangyang Liu, Jianchun Chu, Ziwen Zhang, Maogang He

“…However, it is a challenge to design the ideal IL with the required properties. Variational autoencoders (VAEs) trained by significantly large datasets have shown good performance in drug discovery. …”
Get full text

Variational Generative Adversarial Networks for Preventing Mode Collapse by Mehdi Jamaseb Khollari, Vali Derhami, Mehdi Yazdian Dehkordi

“…This method exploits variational autoencoders to initialize GANs. In other words, in addition to maximizing the variational lower bound, it also implicitly reduces the distance between the two distributions. …”
Get full text

Recent advances for quantum neural networks in generative learning by Tian, Jinkai, Sun, Xiaoyu, Du, Yuxuan, Zhao, Shanshan, Liu, Qing, Zhang, Kaining, Yi, Wei, Huang, Wanrong, Wang, Chaoyue, Wu, Xingyao, Hsieh, Min-Hsiu, Liu, Tongliang, Yang, Wenjing, Tao, Dacheng

“…Particularly, we interpret these QGLMs, covering quantum circuit Born machines, quantum generative adversarial networks, quantum Boltzmann machines, and quantum variational autoencoders, as the quantum extension of classical generative learning models. …”
Get full text

Unsupervised representation learning of Kohn–Sham states and consequences for downstream predictions of many-body effects by Bowen Hou, Jinyuan Wu, Diana Y. Qiu

“…Here, we use variational autoencoders (VAE) for the unsupervised learning of DFT wavefunctions and show that these wavefunctions lie in a low-dimensional manifold within latent space. …”
Get full text

Quantitative evaluation model of variable diagnosis for chest X-ray images using deep learning. by Shota Nakagawa, Naoaki Ono, Yukichika Hakamata, Takashi Ishii, Akira Saito, Shintaro Yanagimoto, Shigehiko Kanaya

“…It was also demonstrated that the developed method could be applied to both transfer learning using convolutional neural networks for general image analysis and a newly learned deep learning model based on vector quantization variational autoencoders with high correlations ranging from 0.89 to 0.97.…”
Get full text

A framework for demonstrating practical quantum advantage: comparing quantum against classical generative models by Mohamed Hibat-Allah, Marta Mauri, Juan Carrasquilla, Alejandro Perdomo-Ortiz

“…In this study, we build over an existing framework for evaluating the generalization performance of generative models, and we establish the first quantitative comparative race towards practical quantum advantage (PQA) between classical and quantum generative models, namely Quantum Circuit Born Machines (QCBMs), Transformers (TFs), Recurrent Neural Networks (RNNs), Variational Autoencoders (VAEs), and Wasserstein Generative Adversarial Networks (WGANs). …”
Get full text

Deep Learning Approaches for 3D Model Generation from 2D Artworks to Aid Blind People with Tactile Exploration by Rocco Furferi

“…The survey explores the potentiality of Convolutional Neural Networks, Generative Adversarial Networks, Variational Autoencoders, and zero-shot methods. Through a small set of case studies, the capabilities and limitations of CNNs in creating a 3D-scene model from artworks are also encompassed. …”
Get full text

Model-based Bayesian inference of neural activity and connectivity from all-optical interrogation of a neural circuit by Aitchison, L, Russell, L, Packer, A, Yan, J, Castonguay, P, Häusser, M, Turaga, S

“…We use the framework of variational autoencoders to model spiking activity using discrete latent variables, low-dimensional latent common input, and sparse spike-and-slab generalized linear coupling between neurons. …”

3D-PhysNet: Learning the intuitive physics of non-rigid object deformations by Wang, Z, Rosa, S, Yang, B, Wang, S, Trigoni, N, Markham, A

“…The key is to combine deep variational autoencoders with adversarial training, conditioned on the applied force and the material properties.We further propose a cascaded architecture that takes a single 2.5D depth view of the object and predicts its deformation. …”

Self-Learning Microfluidic Platform for Single-Cell Imaging and Classification in Flow by Iordania Constantinou, Michael Jendrusch, Théo Aspert, Frederik Görlitz, André Schulze, Gilles Charvin, Michael Knop

“…In this work, we present a microfluidics-based platform for single-cell imaging in-flow and subsequent image analysis using variational autoencoders for unsupervised characterization of cellular mixtures. …”
Get full text

FedLGAN: a method for anomaly detection and repair of hydrological telemetry data based on federated learning by Zheliang Chen, Xianhan Ni, Huan Li, Xiangjie Kong

“…The existing data repair methods primarily focus on addressing missing data issues by utilizing variational autoencoders to learn the underlying distribution and generate content that represents the missing parts, thus achieving data repair. …”
Get full text

Improving novelty detection using the reconstructions of nearest neighbours by Michael Mesarcik, Elena Ranguelova, Albert-Jan Boonstra, Rob V. van Nieuwpoort

“…We validate our method across several standard datasets for a variety of different autoencoding architectures such as vanilla, adversarial and variational autoencoders using either reconstruction, residual or feature consistent losses. …”
Get full text

Incentive temperature control for green colocation data centers via reinforcement learning by Wang, Rongrong, Le, Duc Van, Kang, Jikun, Tan, Rui, Liu, Xue

“…Moreover, as each tenant agent learns in the other tenants' latent state spaces defined by their pre-trained variational autoencoders, only encoded tenants' states are exchanged, thereby mitigating information leakage concerns. …”
Get full text
Get full text

Using deep LSD to build operators in GANs latent space with meaning in real space by J. Quetzalcóatl Toledo-Marín, James A. Glazier

“…Many types of generative model are used in deep learning, e.g., variational autoencoders (VAEs) and generative adversarial networks (GANs). …”
Get full text

Using deep LSD to build operators in GANs latent space with meaning in real space. by J Quetzalcóatl Toledo-Marín, James A Glazier

“…Many types of generative model are used in deep learning, e.g., variational autoencoders (VAEs) and generative adversarial networks (GANs). …”
Get full text

Extracting Interpretable Physical Parameters from Spatiotemporal Systems Using Unsupervised Learning by Peter Y. Lu, Samuel Kim, Marin Soljačić

“…In particular, we implement a physics-informed architecture based on variational autoencoders that is designed for analyzing systems governed by partial differential equations. …”
Get full text