We demonstrate the advantages of using Bayesian neural networks for image analysis. The Bayesian approa h provides onsistent way to do inferen e by ombining the eviden e from data to prior knowledge from the problem. A pra ti al problem with neural networks is to sele t the orre t omplexity for the model, i.e., the right number of hidden units or orre t regularization parameters. The Bayesian a...

We present a simple regularization technique for Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units. Dropout, the most successful technique for regularizing neural networks, does not work well with RNNs and LSTMs. In this paper, we show how to correctly apply dropout to LSTMs, and show that it substantially reduces overfitting on a variety of tasks. These tasks include la...

We propose a modular neural-network structure for implementing the Bayesian framework for learning and inference. Our design has three main components, two for computing the priors and likelihoods based on observations and one for applying Bayes’ rule. Through comprehensive simulations we show that our proposed model succeeds in implementing Bayesian learning and inference. We also provide a no...

Worldwide, conservation agencies employ rangers to protect conservation areas from poachers. However, agencies lack the manpower to have rangers effectively patrol these vast areas frequently. While past work has modeled poachers’ behavior so as to aid rangers in planning future patrols, those models’ predictions were not validated by extensive field tests. In this paper, we present a hybrid sp...

Nowadays 90% of the required water of Iran is secured with groundwater resources and forecasting of pollutants content in these resources is vital. Therefore, this research aimed to develop and employ the feedforward artificial neural network (ANN) to forecast the arsenic (As), lead (Pb), and zinc (Zn) concentration in groundwater resources of Asadabad plain. In this research, the ANN models we...

A deep fully-connected neural network with an i.i.d. prior over its parameters is equivalent to a Gaussian process (GP) in the limit of infinite network width. This correspondence enables exact Bayesian inference for neural networks on regression tasks by means of straightforward matrix computations. For single hiddenlayer networks, the covariance function of this GP has long been known. Recent...

In Bayesian approach to probabilistic modeling of data we select a model for probabilities of data that depends on a continuous vector of parameters. For a given data set Bayesian theorem gives a probability distribution of the model parameters. Then the inference of outcomes and probabilities of new data could be found by averaging over the parameter distribution of the model, which is an intr...

the climate and weather patterns of buffalo (new york, u.s.a.) are strongly influenced by thecity’s proximity to lake erie. total monthly snowfall in buffalo is forecasted using neural network techniques(multi-layer perceptron = mlp) and a multiple linear regression (lr) model. the period of analysis comprises 28 years from january 1982 to december 2009. input data include: zonal wind speed (u-...