22 papers · ranked by Valyu relevance
Zhenwen Dai, Andreas Damianou, Javier González, Neil D. Lawrence
We develop a scalable deep non-parametric generative model by augmenting deep Gaussian processes with a recognition model. Inference is performed in a novel scalable variational framework where the variational posterior distributions are reparametrized through a multilayer perceptron. The key aspect of this…
Kalvik Jakkala
Gaussian processes are one of the dominant approaches in Bayesian learning. Although the approach has been applied to numerous problems with great success, it has a few fundamental limitations. Multiple methods in literature have addressed these limitations. However, there has not been a comprehensive survey of the…
Hugh Salimbeni, Marc Peter Deisenroth
Gaussian processes (GPs) are a good choice for function approximation as they are flexible, robust to overfitting, and provide well-calibrated predictive uncertainty. Deep Gaussian processes (DGPs) are multi-layer generalizations of GPs, but inference in these models has proved challenging. Existing approaches to…
Daniel T. Chang
Probabilistic deep learning is deep learning that accounts for uncertainty, both model uncertainty and data uncertainty. It is based on the use of probabilistic models and deep neural networks. We distinguish two approaches to probabilistic deep learning: probabilistic neural networks and deep probabilistic models. The…
Chi-Ken Lu, Patrick Shafto, Eric Nalisnick, Dustin Tran
It is desirable to combine the expressive power of deep learning with Gaussian Process (GP) in one expressive Bayesian learning model. Deep kernel learning showed success as a deep network used for feature extraction. Then, a GP was used as the function model. Recently, it was suggested that, albeit training with…
Ivan De Boi, Rhys G. Evans, Stuti Pathak, Thomas De Kerf + 5 more
Accurate lens distortion correction is important for calibration, registration, image stitching, and 3D reconstruction, especially in low-data device-specific settings where disposable or specialised cameras cannot provide large calibration datasets. We address distortion correction for cameras with highly irregular or…
Chi-Ken Lu, Scott Cheng‐Hsin Yang, Xiaoran Hao, Patrick Shafto
Deep Gaussian Processes (DGPs) combine the expressiveness of Deep Neural Networks (DNNs) with quantified uncertainty of Gaussian Processes (GPs). Expressive power and intractable inference both result from the non-Gaussian distribution over composition functions. We propose interpretable DGP based on approximating DGP…
Chi-Ken Lu, Patrick Shafto
It is desirable to combine the expressive power of deep learning with Gaussian Process (GP) in one expressive Bayesian learning model. Deep kernel learning showed success in adopting a deep network for feature extraction followed by a GP used as function model. Recently, it was suggested that, albeit training with…
Yikuan Li, Shishir Rao, Abdelaali Hassaine, Rema Ramakrishnan + 5 more
One major impediment to the wider use of deep learning for clinical decision making is the difficulty of assigning a level of confidence to model predictions. Currently, deep Bayesian neural networks and sparse Gaussian processes are the main two scalable uncertainty estimation methods. However, deep Bayesian neural…
Alireza Daneshkhah, Omid Chatrabgoun, Mohsen Esmaeilbeigi, Tabassom Sedighi + 1 more
'Tabassom Sedighi' 'Soroush Abolfathi'] In this paper, we present a computational method on the basis of the non-linear Gaussian process (GP) method, known as deep Gaussian processes (deep GPs) for uncertainty quantification (UQ) and propagation (UP) in modelling of flow through heterogeneous porous media. The method…
Chi-Ken Lu, Patrick Shafto, Eric Nalisnick, Dustin Tran
Deep Gaussian Processes (DGPs) were proposed as an expressive Bayesian model capable of a mathematically grounded estimation of uncertainty. The expressivity of DPGs results from not only the compositional character but the distribution propagation within the hierarchy. Recently, it was pointed out that the…
Thomas Baldwin-McDonald, Xinxing Shi, Mingxin Shen, Mauricio A. Álvarez
'Mauricio A. Álvarez'] Modelling the behaviour of highly nonlinear dynamical systems with robust uncertainty quantification is a challenging task which typically requires approaches specifically designed to address the problem at hand. We introduce a domain-agnostic model to address this issue termed the deep latent…
Tilekbek Zhoroev, Emily F. Hamilton, Philip A. Warrick, Luca Mesin
Clinicians routinely perform pelvic examinations to assess the progress of labor. Clinical guidelines to interpret these examinations, using time-based models of cervical dilation, are not always followed and have not contributed to reducing cesarean-section rates. We present a novel Gaussian process model of labor…
Somya Sharma, Snigdhansu Chatterjee, Eric Nalisnick, Dustin Tran
With the advent of big data and the popularity of black-box deep learning methods, it is imperative to address the robustness of neural networks to noise and outliers. We propose the use of Winsorization to recover model performances when the data may have outliers and other aberrant observations. We provide a…
Eric Schulz, Maarten Speekenbrink, Andreas Krause
This tutorial introduces the reader to Gaussian process regression as a tool to model, actively explore and exploit unknown functions. Gaussian process regression is a powerful, non-parametric Bayesian approach towards regression problems that can be utilized in exploration and exploitation scenarios. This tutorial…
Baptiste Py, Adeleke Maradesa, Francesco Ciucci
Electrochemical impedance spectroscopy (EIS) is a widespread characterization technique used to study electrochemical systems. However, several shortcomings still limit the application of this technique. First, EIS data is intrinsically noisy, hindering spectra regression and prediction at unknown frequencies. Second…
Jonas Verhellen
In recent years, there have been considerable academic and industrial research efforts to develop novel generative models for high-performing, small molecules. Traditional, rules-based algorithms such as genetic algorithms [Jensen, Chem. Sci., 2019, 12, 3567-3572] have, however, been shown to rival deep learning…
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…
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…
Sterling Baird, Jason R. Hall, Taylor D. Sparks
Would you rather search for a line inside a cube or a point inside a square? Physics-based simulations and wet-lab experiments often have symmetries (degeneracies) that allow reducing problem dimensionality or search space, but constraining these degeneracies is often unsupported or difficult to implement in many…
Sterling Baird, Jason R. Hall, Taylor D. Sparks
Would you rather search for a line inside a cube or a point inside a square? This type of solution degeneracy often exists in physics-based simulations and wet-lab experiments, but constraining these degeneracies is often unsupported or difficult to implement in many optimization packages, requiring additional time and…
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…