Transfer learning is a machine technique that uses previously acquired knowledge from source domain to enhance in target by reusing learned weights. This ubiquitous because of its great advantages achieving high performance while saving training time, memory, and effort network design. In this paper, we investigate how select the best pre-trained model meets requirements for image classificatio...

In recent years, Deep Learning at the latest developed field belonging to soft computing. The Deep learning has been a hot topic in the communities of artificial intelligence, artificial neural networks and machine learning. It tries to mimic the human brain, which is capable of processing the intricate input data, learning various knowledge’s intellectually and intense as well as solving sundr...

We develop and test three deep-learning recurrent convolutional architectures for learning to recognize single trial EEG event related potentials for P300 brain-computer interfaces (BCI)s. One advantage of the neural network solution is that it provides a natural way to share a lower-level feature space between subjects while adapting the classifier that works on that feature space. We compare ...

In classification tasks, restricted Boltzmann machines (RBMs) have predominantly been used in the first stage, either as feature extractors or to provide initialization of neural networks. In this study, we propose a discriminative learning approach to provide a self-contained RBM method for classification, inspired by free-energy based function approximation (FE-RBM), originally proposed for r...

This paper extends our previous work on regularization of neural networks using Eigenvalue Decay by employing a soft approximation of the dominant eigenvalue in order to enable the calculation of its derivatives in relation to the synaptic weights, and therefore the application of back-propagation, which is a primary demand for deep learning. Moreover, we extend our previous theoretical analysi...

TextCNN, the convolutional neural network for text, is a useful deep learning algorithm for sentence classification tasks such as sentiment analysis and question classification[2]. However, neural networks have long been known as black boxes because interpreting them is a challenging task. Researchers have developed several tools to understand a CNN for image classification by deep visualizatio...

The paper presents a design of parameters for air quality modelling and the classification of districts into classes according to their pollution. Further, it presents a model design, data pre-processing, the designs of various structures of Kohonen’s Self-organizing Feature Maps (unsupervised methods), the clustering by K-means algorithm and the classification by Learning Vector Quantization n...