Search Results

An improved version of the Selective Backpropagation (SBP+) is described which significantly reduces the training time and enhances the generalization. The algorithm eliminates correctly predicted instances from the Backpropagation (BP) in an ...

• Improved Selective Backpropagation is described which accelerates training.
• Acceleration is due to the elimination of accurate predictions from backpropagation.
• Improvement in accuracy is due to the inclusion of random error term.

We implement deep learning for predicting bitcoin closing prices. Identifying two new determiners, we propose a novel LSTM Autoencoder using Mean Squared Error (MSE) loss which is regularized by False Nearest Neighbor (FNN) algorithm. The method ...

Named entity recognition (NER) is to identify and categorize entities in unstructured text, which serves as a fundamental task for a variety of natural language processing (NLP) applications. In particular, emerging few-shot NER methods aim to ...

• This paper highlights the contribution of the semantic distribution distance constraints on general knowledge transfer.
• The proposed approach is a common framework without adding extra learning parameters.
• Extensive experiments ...

Pi-sigma neural network (PSNN) is a class of high order feed-forward neural networks with product units in the output layer, which leads to its fast convergence speed and a high degree of nonlinear mapping capability. Inspired by the sparse ...

Fast adversarial training (FAT) effectively improves the efficiency of standard adversarial training (SAT). However, initial FAT encounters catastrophic overfitting, i.e., the robust accuracy against adversarial attacks suddenly and dramatically ...

With the developments of smart city, wireless passive localization (WPL) technique that detects targets without carrying any devices draws a lot of research attention. Some machine learning methods, such as sparse coding and deep learning, have ...

In present study, we proposed a general framework based on a convolutional kernel and a variational autoencoder (CVAE) for anomaly detection on both complex image and vector datasets. The main idea is to maximize mutual information (MMI) through ...

Learning and reasoning over graphs is increasingly done by means of probabilistic models, e.g. exponential random graph models, graph embedding models, and graph neural networks. When graphs are modeling relations between people, however, they ...

• Introduce regularizer based on the number of isolated objects for small vessel segmentation.
• The number of isolated objects estimate from the topology of segmentation result by using Euler characteristics.
• Euler characteristic-...

Segmentation of retinal blood vessels is important for the analysis of diabetic retinopathy (DR). Existing methods do not prioritize the small and disconnected vessels for DR. With the aim of paying attention to the small and disconnected vessel ...

We revisit the benefits of merging classical vision concepts with deep learning models. In particular, we explore the effect of replacing the first layers of various deep architectures with Gabor layers (i.e. convolutional layers with filters that ...

In recent years, concept factorization methods become a popular data representation technique in many real applications. However, conventional concept factorization methods cannot capture the intrinsic geometric structure embedded in data using ...

This paper investigates the split complex gradient descent based neuro-fuzzy algorithm with self-adaptive momentum and L ₂ regularizer for training TSK (Takagi–Sugeno–Kang) fuzzy inference models. The major threat for disposing complex data with ...

This paper suggests a convex regularized optimization model to produce recommendations, which is adaptable, fast, and scalable--while remaining very competitive to state-of-the-art methods in terms of accuracy. We introduce a regularizer based on the ...

Recently, sparse coding has been widely adopted for data representation in real-world applications. In order to consider the geometric structure of data, we propose a novel method, local and global regularized sparse coding (LGSC), for data ...

Sparse representation (SR) based dimension reduction (DR) methods have aroused lots of interests in the field of face recognition. In this paper, we firstly propose a new sparse representation method called weighted elastic net (WEN). Compared to the ...

A new understanding of the notion of the stable solution to ill-posed problems is proposed. The new notion is more realistic than the old one and better fits the practical computational needs. A method for constructing stable solutions in the new sense ...

In this paper we proposed two new variants of backpropagation algorithm. The common point of these two new algorithms is that the outputs of nodes in the hidden layers are controlled with the aim to solve the moving target problem and the distributed ...