Analysis and forecasting of sequential data, key problems in various domains of engineering and science, have attracted the attention of many researchers from different communities. When predicting the future probability of events using time series, ...
The success of CNNs is accompanied by deep models and heavy storage costs. For compressing CNNs, we propose an efficient and robust pruning approach, cross-entropy pruning (CEP). Given a trained CNN model, connections were divided into groups in a gr...
Intracortical brain computer interfaces can enable individuals with paralysis to control external devices through voluntarily modulated brain activity. Decoding quality has been previously shown to degrade with signal nonstationarities-specifically, ...
Simulation of the cerebral cortex requires a combination of extensive domain-specific knowledge and efficient software. However, when the complexity of the biological system is combined with that of the software, the likelihood of coding errors incre...
This study focuses on predicting stock closing prices by using recurrent neural networks (RNNs). A long short-term memory (LSTM) model, a type of RNN coupled with stock basic trading data and technical indicators, is introduced as a novel method to p...
Biological networks have long been known to be modular, containing sets of nodes that are highly connected internally. Less emphasis, however, has been placed on understanding how intermodule connections are distributed within a network. Here, we bor...
As the optical lenses for cameras always have limited depth of field, the captured images with the same scene are not all in focus. Multifocus image fusion is an efficient technology that can synthesize an all-in-focus image using several partially f...
Transposition is a tendency for organisms to generalize relationships between stimuli in situations where training does not objectively reward relationships over absolute, static associations. Transposition has most commonly been explained as either ...
We propose a neural network model for reinforcement learning to control a robotic manipulator with unknown parameters and dead zones. The model is composed of three networks. The state of the robotic manipulator is predicted by the state network of t...
To accommodate structured approaches of neural computation, we propose a class of recurrent neural networks for indexing and storing sequences of symbols or analog data vectors. These networks with randomized input weights and orthogonal recurrent we...