Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding

9 Nov 201513 code implementations

Semantic segmentation is an important tool for visual scene understanding and a meaningful measure of uncertainty is essential for decision making.

DECISION MAKING SCENE UNDERSTANDING SEMANTIC SEGMENTATION

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

6 Jun 201512 code implementations

In comparison, Bayesian models offer a mathematically grounded framework to reason about model uncertainty, but usually come with a prohibitive computational cost.

BAYESIAN INFERENCE GAUSSIAN PROCESSES

Practical Bayesian Optimization for Model Fitting with Bayesian Adaptive Direct Search

NeurIPS 2017 2 code implementations

Computational models in fields such as computational neuroscience are often evaluated via stochastic simulation or numerical approximation.

Bayesian Modeling with Gaussian Processes using the GPstuff Toolbox

25 Jun 20121 code implementation

The prior over functions is defined implicitly by the mean and covariance function, which determine the smoothness and variability of the function.

GAUSSIAN PROCESSES

ZhuSuan: A Library for Bayesian Deep Learning

18 Sep 20171 code implementation

In this paper we introduce ZhuSuan, a python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and deep learning.

PROBABILISTIC PROGRAMMING

Making Tree Ensembles Interpretable: A Bayesian Model Selection Approach

29 Jun 20161 code implementation

In this study, we present a method to make a complex tree ensemble interpretable by simplifying the model.

MODEL SELECTION

Embedding Words as Distributions with a Bayesian Skip-gram Model

COLING 2018 1 code implementation

Rather than assuming that a word embedding is fixed across the entire text collection, as in standard word embedding methods, in our Bayesian model we generate it from a word-specific prior density for each occurrence of a given word.

Bayesian Model-Agnostic Meta-Learning

NeurIPS 2018 2 code implementations

Learning to infer Bayesian posterior from a few-shot dataset is an important step towards robust meta-learning due to the model uncertainty inherent in the problem.

ACTIVE LEARNING IMAGE CLASSIFICATION META-LEARNING

Bayesian Subspace Hidden Markov Model for Acoustic Unit Discovery

8 Apr 20191 code implementation

This work tackles the problem of learning a set of language specific acoustic units from unlabeled speech recordings given a set of labeled recordings from other languages.