Related papers: Effects of padding on LSTMs and CNNs

Recently, several methods have been proposed to explain the predictions of recurrent neural networks (RNNs), in particular of LSTMs. The goal of these methods is to understand the network's decisions by assigning to each input variable,…

Machine learning (ML) tools such as encoder-decoder convolutional neural networks (CNN) can represent incredibly complex nonlinear functions which map between combinations of images and scalars. For example, CNNs can be used to map…

In recent years, deep learning methods have achieved great success in various fields due to their strong performance in practical applications. In this paper, we present a light-weight neural network for Parkinson's disease diagnostics, in…

Convolutional neural networks (CNNs) are commonly used for image classification. Saliency methods are examples of approaches that can be used to interpret CNNs post hoc, identifying the most relevant pixels for a prediction following the…

Recent years, the approaches based on neural networks have shown remarkable potential for sentence modeling. There are two main neural network structures: recurrent neural network (RNN) and convolution neural network (CNN). RNN can capture…

When applying a convolutional kernel to an image, if the output is to remain the same size as the input then some form of padding is required around the image boundary, meaning that for each layer of convolution in a convolutional neural…

This paper have two parts. In the first part we discuss word embeddings. We discuss the need for them, some of the methods to create them, and some of their interesting properties. We also compare them to image embeddings and see how word…

Network Traffic Matrix (TM) prediction is defined as the problem of estimating future network traffic from the previous and achieved network traffic data. It is widely used in network planning, resource management and network security. Long…

Hyper spectral images have drawn the attention of the researchers for its complexity to classify. It has nonlinear relation between the materials and the spectral information provided by the HSI image. Deep learning methods have shown…

The success of Convolutional Neural Networks (CNNs) in computer vision is mainly driven by their strong inductive bias, which is strong enough to allow CNNs to solve vision-related tasks with random weights, meaning without learning.…

We propose a new model for unsupervised document embedding. Leading existing approaches either require complex inference or use recurrent neural networks (RNN) that are difficult to parallelize. We take a different route and develop a…

During the last decades, many studies have been dedicated to improving the performance of neural networks, for example, the network architectures, initialization, and activation. However, investigating the importance and effects of…

Spiking Neural Networks (SNN) have gained increasing attention for its low power consumption. But training SNN is challenging. Liquid State Machine (LSM), as a major type of Reservoir computing, has been widely recognized for its low…

Sentence-level classification and sequential labeling are two fundamental tasks in language understanding. While these two tasks are usually modeled separately, in reality, they are often correlated, for example in intent classification and…

Recurrent neural networks (RNNs), including long short-term memory (LSTM) RNNs, have produced state-of-the-art results on a variety of speech recognition tasks. However, these models are often too large in size for deployment on mobile…

The recognition and classification of the diversity of materials that exist in the environment around us are a key visual competence that computer vision systems focus on in recent years. Understanding the identification of materials in…

Convolutional Neural Networks (CNNs) have achieved comparable error rates to well-trained human on ILSVRC2014 image classification task. To achieve better performance, the complexity of CNNs is continually increasing with deeper and bigger…

Recurrent neural networks (RNNs) have many advantages over more traditional system identification techniques. They may be applied to linear and nonlinear systems, and they require fewer modeling assumptions. However, these neural network…

Offline handwriting recognition systems require cropped text line images for both training and recognition. On the one hand, the annotation of position and transcript at line level is costly to obtain. On the other hand, automatic line…

Long-range sequence modeling is a crucial aspect of natural language processing and time series analysis. However, traditional models like Recurrent Neural Networks (RNNs) and Transformers suffer from computational and memory…