Search

Deep convolutional neural networks (DCNNs) have dominated as the best performers on almost all computer vision tasks over the past several years. However, it remains a major challenge to deploy these powerful DCNNs in resource-limited environments, such as embedded devices and smartphones. To this end, 1-bit CNNs have emerged as a feasible solution as they are much more resource-efficient. Unfortunately, they often suffer from a significant performance drop compared to their full-precision counterparts. In this paper, we propose a novel Bayesian Optimized compact 1-bit CNNs (BONNs) model, which has the advantage of Bayesian learning, to improve the performance of 1-bit CNNs significantly. BONNs incorporate the prior distributions of full-precision kernels, features, and filters into a Bayesian framework to construct 1-bit CNNs in a comprehensive end-to-end manner. The proposed Bayesian learning algorithms are well-founded and used to optimize the network simultaneously in different kernels, features, and filters, which largely improves the compactness and capacity of 1-bit CNNs. We further introduce a new Bayesian learning-based pruning method for 1-bit CNNs, which significantly increases the model efficiency with very competitive performance. This enables our method to be used in a variety of practical scenarios. Extensive experiments on the ImageNet, CIFAR, and LFW datasets show that BONNs achieve the best in classification performance compared to a variety of state-of-the-art 1-bit CNN models. In particular, BONN achieves a strong generalization performance on the object detection task. [ABSTRACT FROM AUTHOR]

Neural network (NN) finds role in variety of applications due to combined effect of feature extraction and classification availability in deep learning algorithms. In this paper, we have chosen SVM, logistic regression machine learning algorithms and NN for EEG signal classification. Two-layer LSTM and four-layer improved NN deep learning algorithms are proposed to improve the performance in EEG classification. Novelty lies in one-dimensional gradient descent activation functions with radial basis operations used in the initial layers of improved NN which help in achieving better performance. Statistical features namely mean, standard deviation, kurtosis and skewness are extracted for input EEG collected from Bonn database and then applied for various classification techniques. Accuracy, precision, recall and F1 score are the performance metrics used for analyzing the algorithms. Improved NN and LSTM give better performance compared to all other architectures. The simulations are carried out with variety of activation functions, optimizers and loss models to analyze the performance using Python in keras. [ABSTRACT FROM AUTHOR]