23 papers · ranked by Valyu relevance
Javier Antorán, James Urquhart Allingham, José Miguel Hernández-Lobato
'José Miguel Hernández-Lobato'] One-shot neural architecture search allows joint learning of weights and network architecture, reducing computational cost. We limit our search space to the depth of residual networks and formulate an analytically tractable variational objective that allows for obtaining an unbiased…
Laith Alzubaidi, Jinglan Zhang, Amjad J. Humaidi, Ayad Al-Dujaili + 6 more
In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in the field of ML, thus achieving outstanding results on several complex cognitive tasks, matching or…
Jan Steinbrener, Konstantin Posch, Jürgen Pilz
We present a novel approach for training deep neural networks in a Bayesian way. Compared to other Bayesian deep learning formulations, our approach allows for quantifying the uncertainty in model parameters while only adding very few additional parameters to be optimized. The proposed approach uses variational…
Lei Cai, Hongyang Gao, Shuiwang Ji
Variational auto-encoder (VAE) is a powerful unsupervised learning framework for image generation. One drawback of VAE is that it generates blurry images due to its Gaussianity assumption and thus `2 loss. To allow the generation of high quality images by VAE, we increase the capacity of decoder network by employing…
Max Highsmith, Jianlin Cheng
Chromatin conformation plays an important role in a variety of genomic processes. Hi-C is one of the most popular assays for inspecting chromatin conformation. However, the utility of Hi-C contact maps is bottlenecked by resolution. Here we present VEHiCLE, a deep learning algorithm for resolution enhancement of Hi-C…
Darius Chira, Ilian Haralampiev, Ole Winther, Andrea Dittadi + 1 more
'Valentin Liévin'] Abstract. Image super-resolution (SR) techniques are used to generate a high-resolution image from a low-resolution image. Until now, deep generative models such as autoregressive models and Generative Adversarial Networks (GANs) have proven to be effective at modelling highresolution images.…
Xu Pan, Ruben Coen-Cagli, Odelia Schwartz
Convolutional neural networks (CNNs) have been used to model the biological visual system. Compared to other models, CNNs can better capture neural responses to natural stimuli. However, previous successes are limited to modeling mean responses; while another fundamental aspect of cortical activity, namely response…
Pavel Kohout, Michal Vasina, Marika Majerova, Veronika Novakova + 5 more
Enzymes play a crucial role in sustainable industrial applications, with their optimization posing a formidable challenge due to the intricate interplay among residues. Computational methodologies predominantly rely on evolutionary insights, leveraging homologous sequences to pinpoint conserved and functionally…
Xianxu Hou, Ke Sun, Linlin Shen, Guoping Qiu
We present a new method for improving the performances of variational autoencoder (VAE). In addition to enforcing the deep feature consistent principle thus ensuring the VAE output and its corresponding input images to have similar deep features, we also implement a generative adversarial training mechanism to force…
Huaibo Huang, Lingxiao Song, Ran He, Zhenan Sun + 1 more
A capsule is a group of neurons whose activity vector models different properties of the same entity. This paper extends the capsule to a generative version, named variational capsules (VCs). Each VC produces a latent variable for a specific entity, making it possible to integrate image analysis and image synthesis…
Kuo-Hao Fanchiang, Cheng-Chien Kuo, Anastasios Doulamis
Dry-type power transformers play a critical role in the power system. Detecting various overheating faults in the running state of the power transformer is necessary to avoid the collapse of the power system. In this paper, we propose a novel deep variational autoencoder-based anomaly detection method to recognize the…
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…
Ran Liu, Cem Subakan, Aishwarya H. Balwani, Jennifer Whitesell + 3 more
Understanding how neural structure varies across individuals is critical for characterizing the effects of disease, learning, and aging on the brain. However, disentangling the different factors that give rise to individual variability is still an outstanding challenge. In this paper, we introduce a deep generative…
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…
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…
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…
Jessica Loke, Noor Seijdel, Lukas Snoek, Matthew van der Meer + 4 more
Recurrent processing is a crucial feature in human visual processing supporting perceptual grouping, figure-ground segmentation, and recognition under challenging conditions. There is a clear need to incorporate recurrent processing in deep convolutional neural networks (DCNNs) but the computations underlying recurrent…
Ian Fischer, Alexander A. Alemi
Intuitively, one way to make classifiers more robust to their input is to have them depend less sensitively on their input. The Information Bottleneck (IB) tries to learn compressed representations of input that are still predictive. Scaling up IB approaches to large scale image classification tasks has proved…
Kevin Linka, Gerhard A Holzapfel, Ellen Kuhl
Understanding uncertainty is critical, especially when data are sparse and variations are large. Bayesian neural networks offer a powerful strategy to build predictable models from sparse data, and inherently quantify both, aleatoric uncertainties of the data and epistemic uncertainties of the model. Yet, classical…
Benjamin Hoar, Weitong Zhang, Shuangning Xu, Rana Deeba + 3 more
For decades, employing cyclic voltammetry for mechanistic investigation demands manual inspection of voltammograms. Here we report a deep-learning-based algorithm that automatically analyzes cyclic voltammograms and designates a electrochemical probable mechanism among five of the most common ones in homogenous…
R. Ian Etheredge, Manfred Schartl, Alex Jordan
Apart from discriminative models for classification and object detection tasks, the application of deep convolutional neural networks to basic research utilizing natural imaging data has been somewhat limited; particularly in cases where a set of interpretable features for downstream analysis is needed, a key…
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…
Sanjar Adilov
Generative neural networks have shown promising results in de novo drug design. Recent studies suggest that one of the efficient ways to produce novel molecules matching target properties is to model SMILES sequences using deep learning in a way similar to language modeling in natural language processing. In this…