A challenge that machine learning practitioners in the industry face is the task of selecting the best model to deploy in production.
Our derived analytical results are exact and apply for small as well as complex neural networks for decoder and encoder.
We present a novel approach to Bayesian inference and general Bayesian computation that is defined through a sequential decision loop.
The library widens the scope of dictionary learning approaches beyond implementations of standard approaches such as ICA, NMF or standard L1 sparse coding.
Bayesian optimization (BO) methods often rely on the assumption that the objective function is well-behaved, but in practice, this is seldom true for real-world objectives even if noise-free observations can be collected.
Despite the recent progress in hyperparameter optimization (HPO), available benchmarks that resemble real-world scenarios consist of a few and very large problem instances that are expensive to solve.
A probabilistic module consists of a set of random variables with associated probabilistic distributions and dedicated inference methods.
We further demonstrate the strength of our method on knowledge transfer across heterogeneous network architectures by transferring knowledge from a convolutional neural network (CNN) to a multi-layer perceptron (MLP) on CIFAR-10.
We tackle the problem of optimizing a black-box objective function defined over a highly-structured input space.
in-GPs respect the potentially complex boundary or interior conditions as well as the intrinsic geometry of the spaces.
We investigate the optimization of two probabilistic generative models with binary latent variables using a novel variational EM approach.
Development systems for deep learning (DL), such as Theano, Torch, TensorFlow, or MXNet, are easy-to-use tools for creating complex neural network models.
We present a new framework for this scenario that we call Preferential Bayesian Optimization (PBO) and that allows to find the optimum of a latent function that can only be queried through pairwise comparisons, so-called duels.
Often in machine learning, data are collected as a combination of multiple conditions, e. g., the voice recordings of multiple persons, each labeled with an ID.
Bayesian optimization (BO) has emerged during the last few years as an effective approach to optimizing black-box functions where direct queries of the objective are expensive.
The spatio-temporal field of protein concentration and mRNA expression are reconstructed without explicitly solving the partial differential equation.
Unsupervised learning on imbalanced data is challenging because, when given imbalanced data, current model is often dominated by the major category and ignores the categories with small amount of data.
We define Recurrent Gaussian Processes (RGP) models, a general family of Bayesian nonparametric models with recurrent GP priors which are able to learn dynamical patterns from sequential data.
We develop a scalable deep non-parametric generative model by augmenting deep Gaussian processes with a recognition model.
The approach assumes that the function of interest, $f$, is a Lipschitz continuous function.
The Gaussian process latent variable model (GP-LVM) is a popular approach to non-linear probabilistic dimensionality reduction.
We propose a nonparametric procedure to achieve fast inference in generative graphical models when the number of latent states is very large.
In this work, we present an extension of Gaussian process (GP) models with sophisticated parallelization and GPU acceleration.
By far most approaches to unsupervised learning learning of visual features, such as sparse coding or ICA, account for translations by representing the same features at different positions.