ACL Anthology About Announcements Communication channels Related work Copyright Credits Volunteer Development Feedback Using Citing papers Links in the Anthology Data access All FAQs Details Anthology identifiers Names ORCID iDs DOIs Verified authors Contributions Submissions Corrections Author pages Attachments GitHub Can Neural Networks Understand Monotonicity Reasoning? Hitomi Yanaka , Koji Mineshima , Daisuke Bekki , Kentaro Inui , Satoshi Sekine , Lasha Abzianidze , Johan Bos Correct Metadata for Use t

Convolutional Neural Networks (CNNs) have become indispensable for solving machine learning tasks in speech recognition, computer vision, and other areas that involve high-dimensional data. A CNN filters the input feature using a network containing spatial convolution operators with compactly supported stencils. In practice, the input data and the hidden features consist of a large number of channels, which in most CNNs are fully coupled by the convolution operators. This coupling leads to immense computati

Abstract page for arXiv paper 2208.07998: What Artificial Neural Networks Can Tell Us About Human Language Acquisition

Spiking Networks as Non Local Cellular Automata In this paper, we propose a novel regularization method for spiking neural networks. We note the similarities of a spiking network to a non local cellular automaton and de

Knowledge Distillation technique converts Deep Neural Networks into decision trees to achieve both high accuracy and interpretability without sacrificing model performance

A Feed Forward Neural Network is an artificial neural network in which the connections between nodes does not form a cycle. The opposite of a feed forward neural network is a recurrent neural network, in which certain pathways are cycled

A concise guide to assessing your neural network's feature importance

Deep learning teaches machines to find patterns in raw data through layered neural networks. See how it works and how it differs from machine learning

In this blog, we will learn about the essential task of assessing the accuracy and performance of neural networks, a critical aspect for data scientists and software engineers engaged in building and training such networks. Delving into the post-training phase, we will explore the significance of calculating errors to ensure optimal functionality. The article will elaborate on various types of errors encountered in neural networks and provide insights into the methods for their precise calculation

While neural networks perform well on image, text, and audio datasets, they fall behind decision trees and their variations for tabular datasets. New research