Many of the similarity-based virtual screening approaches assume that molecular fragments that are not related to the biological activity carry the same weight as the important ones. This was the reason that led to the use of Bayesian networks as an alternative to existing tools for similarity-based virtual screening. In our recent work, the retrieval performance of the Bayesian inference netwo...

Due to the chaotic nature of multilayer perceptron training, training error usually fails to be a monotonically nonincreasing function of the number of hidden units. New training algorithms are developed where weights and thresholds from a well-trained smaller network are used to initialize a larger network. Methods are also developed to reduce the total amount of training required. It is shown...

| First, an evolutionary algorithm for designing a single hidden layer feedfor-ward neural networks is proposed. The algorithm constructs a problem tailored neu-ral network by incremental introduction of new hidden units. Each new hidden unit is added to the network by linear partitioning of the hidden-layer representation through a genetic search. Second, a two stage algorithm speed-up is achi...

Stock performance modeling using neural networks: A comparative study with regression models', Neural Networks. fully connected network, it is not sufficient to stop removing weights when b P() first increases. This is particularly true given that both SBP and OBD are greedy algorithms, and they neglect interactions between multiple inputs and weights. Thus, removing additional inputs or weight...

We present a new patch-based image restoration algorithm using an adaptive Wiener filter (AWF) with a novel spatial-domain multi-patch correlation model. The new filter structure is referred to as a collaborative adaptive Wiener filter (CAWF). The CAWF employs a finite size moving window. At each position, the current observation window represents the reference patch. We identify the most simil...

Convolutional neural networks (CNNs) have been successfully applied to many tasks such as digit and object recognition. Using convolutional (tied) weights significantly reduces the number of parameters that have to be learned, and also allows translational invariance to be hard-coded into the architecture. In this paper, we consider the problem of learning invariances, rather than relying on ha...

Performance measurement, as an effective tool for implementing organizational strategy and assisting ongoing control and surveillance, is broadly adopted today. The performance measurement system (PMS) explored in this case study was implemented, using business intelligence (BI) technologies, for a public police force. The system lets police commanders view and analyze the performance scores of...

Extreme Learning Machine (ELM) is a neural network architecture in which hidden layer weights are randomly chosen and output layer weights determined analytically. We interpret ELM as an approximation to a network with infinite number of hidden units. The operation of the infinite network is captured by neural network kernel (NNK). We compare ELM and NNK both as part of a kernel method and in n...