Results 81 to 90 of about 1,922 (260)
On Georgian Handwritten Character Recognition
Abstract The article addresses the issue of Georgian handwritten text recognition. As a result of the performed research activity, a framework for recognizing handwritten Georgian text using Self-Normalizing Convolutional Neural Networks (CNN) was developed. To train the CNN model, an extensive dataset was created with over 200 000 character samples.
Davit Soselia +5 more
openaire +1 more source
Exploiting Ferroelectric and Spintronic Dynamics for Neural Network Computation
Ferroelectric and spintronic devices, relying on the control of polarization and magnetization, offer intrinsically fast, durable, energy‐efficient, and low‐latency building blocks for analog in‐memory computing. The hysteretic dynamics of an order parameter are leveraged to provide nonvolatile, multistate memory and nonlinear switching. Brain‐inspired
Dashiell Harrison +4 more
wiley +1 more source
Abstract Maternal and neonatal morbidity and mortality have declined dramatically during the last century. Historical data are therefore important sources to study the evolutionary selection pressures related to childbirth and how they have fluctuated over time.
Mirella Woodert +7 more
wiley +1 more source
Charlotte Pommer: Resistance fighter and female pioneer of German anatomy
Abstract This article examines the biography and unique case of Charlotte Pommer (1914–2004), the only anatomist documented to have left the field during the Nazi period after encountering the regime's victims on the dissection table. While she is known for her resistance activities, newly presented documentation reveals her role as the provisional ...
Tim S. Goldmann
wiley +1 more source
Automated character recognition is currently highly popular due to its wide range of applications. Bengali handwritten character recognition (BHCR) is an extremely difficult issue because of the nature of the script.
Mirza Raquib +3 more
doaj +1 more source
Abstract Context‐centric proactive information delivery (PID) is a relatively underexplored domain within recommender systems (RS) aimed at enhancing Knowledge Workers' productivity by proactively providing relevant information during digital tasks.
Mahta Bakhshizadeh +4 more
wiley +1 more source
AI voice journaling for future language teachers: A path to well‐being through reflective practices
Abstract This study aimed to explore the perceived impact of using an AI‐powered voice journaling app in overcoming the challenges and stressors encountered by senior students enrolled in teaching practicum at an English Language Teaching Bachelor's programme.
Bora Demir, Duygu Özdemir
wiley +1 more source
Kurdish standard EMNIST-like character dataset
A dataset was created by collecting handwritten samples of distinct Kurdish characters. The dataset consists primarily of 58 characters, and approximately 3800 adult volunteers who are native Kurdish speakers participated in the collection process.
Hamsa D. Majeed +3 more
doaj +1 more source
Contrasting roles of school and public libraries in lower primary pupils' reading
Abstract Libraries represent an important institutional component of children's reading socialisation, yet their role is often treated as uniform despite substantial differences between school and public libraries. This study examines how visits to school and public libraries relate to pupils' reading attitudes, practices and self‐assessed reading ...
Kateřina Balcarová, Jiří Balcar
wiley +1 more source
Learning Based Ge'ez Character Handwritten Recognition
Ge'ez, an ancient Ethiopic script of cultural and historical significance, has been largely neglected in handwriting recognition research, hindering the digitization of valuable manuscripts. Our study addresses this gap by developing a state-of-the-art Ge'ez handwriting recognition system using Convolutional Neural Networks (CNNs) and Long Short-Term ...
Hailemicael Lulseged Yimer +3 more
openaire +2 more sources

