Related papers: PepCVAE: Semi-Supervised Targeted Design of Antimi…
Although artificial neural networks are often described as brain-inspired, their representations typically rely on continuous activations, such as the continuous latent variables in variational autoencoders (VAEs), which limits their…
Disentangled generative models map a latent code vector to a target space, while enforcing that a subset of the learned latent codes are interpretable and associated with distinct properties of the target distribution. Recent advances have…
The chemical space of drug-like molecules is vast, motivating the development of generative models that must learn broad chemical distributions, enable conditional generation by capturing structure-property representations, and provide fast…
Cyclic peptides, characterized by geometric constraints absent in linear peptides, offer enhanced biochemical properties, presenting new opportunities to address unmet medical needs. However, designing target-specific cyclic peptides…
Metamaterials are emerging as a new paradigmatic material system to render unprecedented and tailorable properties for a wide variety of engineering applications. However, the inverse design of metamaterial and its multiscale system is…
Reliable fault detection is an essential requirement for safe and efficient operation of complex mechanical systems in various industrial applications. Despite the abundance of existing approaches and the maturity of the fault detection…
Semi-supervised classification is a great focus of interest, as in real-world scenarios obtaining labels is expensive, time-consuming and might require expert knowledge. This has motivated the fast development of semi-supervised techniques,…
Deep generative models (DGMs) have achieved remarkable advances. Semi-supervised variational auto-encoders (SVAE) as a classical DGM offer a principled framework to effectively generalize from small labelled data to large unlabelled ones,…
Gastrointestinal (GI) imaging via Wireless Capsule Endoscopy (WCE) generates a large number of images requiring manual screening. Deep learning-based Clinical Decision Support (CDS) systems can assist screening, yet their performance relies…
We present a new flavor of Variational Autoencoder (VAE) that interpolates seamlessly between unsupervised, semi-supervised and fully supervised learning domains. We show that unlabeled datapoints not only boost unsupervised tasks, but also…
Deep supervised neural networks trained to classify objects have emerged as popular models of computation in the primate ventral stream. These models represent information with a high-dimensional distributed population code, implying that…
Noninvasive reconstruction of cardiac transmembrane potential (TMP) from surface electrocardiograms (ECG) involves an ill-posed inverse problem. Model-constrained regularization is powerful for incorporating rich physiological knowledge…
Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of…
Automatically designing fast and space-efficient digital circuits is challenging because circuits are discrete, must exactly implement the desired logic, and are costly to simulate. We address these challenges with CircuitVAE, a search…
Understanding the structure of complex, nonstationary, high-dimensional time-evolving signals is a central challenge in scientific data analysis. In many domains, such as speech and biomedical signal processing, the ability to learn…
Deep learning has demonstrated significant improvements in medical image segmentation using a sufficiently large amount of training data with manual labels. Acquiring well-representative labels requires expert knowledge and exhaustive…
Recent advances have shown that GP priors, or their finite realisations, can be encoded using deep generative models such as variational autoencoders (VAEs). These learned generators can serve as drop-in replacements for the original priors…
By integrating various simulation and experimental techniques, we discovered that antimicrobial peptides (AMPs) may achieve synergy at an optimal concentration and ratio, which can be caused by aggregation of the synergistic peptides. On…
Traditional non-biological storage media, such as hard drives, face limitations in both storage density and lifespan due to the rapid growth of data in the big data era. Mirror-image peptides composed of D-amino acids have emerged as a…
Controllable text generation has taken a gigantic step forward these days. Yet existing methods are either constrained in a one-off pattern or not efficient enough for receiving multiple conditions at every generation stage. We propose a…