Qurating: Selecting high-quality data for training language models
Selecting high-quality pre-training data is important for creating capable language models,
but existing methods rely on simple heuristics. We introduce QuRating, a method for …
but existing methods rely on simple heuristics. We introduce QuRating, a method for …
Deep convolutional forest: a dynamic deep ensemble approach for spam detection in text
The increase in people's use of mobile messaging services has led to the spread of social
engineering attacks like phishing, considering that spam text is one of the main factors in the …
engineering attacks like phishing, considering that spam text is one of the main factors in the …
[HTML][HTML] How AI can be used for governance of messaging services: A study on spam classification leveraging multi-channel convolutional neural network
Over the past decade, there has been a meteoric evolution in Internet Messaging Services
and although these services have become ingrained in our everyday life, SMS service …
and although these services have become ingrained in our everyday life, SMS service …
Large language models are zero-shot text classifiers
Retrained large language models (LLMs) have become extensively used across various sub-
disciplines of natural language processing (NLP). In NLP, text classification problems have …
disciplines of natural language processing (NLP). In NLP, text classification problems have …
An 8-bit single perceptron processing unit for tiny machine learning applications
We present a tiny MultiLayer Perceptron (MLP) accelerator named Single Perceptron Linear
Vector Processor (SPLVP) that aims at extending the capabilities of limited resources MCUs …
Vector Processor (SPLVP) that aims at extending the capabilities of limited resources MCUs …
[HTML][HTML] EGMA: Ensemble Learning-Based Hybrid Model Approach for Spam Detection
Spam messages have emerged as a significant issue in digital communication, adversely
affecting users' mental health, personal safety, and network resources. Traditional spam …
affecting users' mental health, personal safety, and network resources. Traditional spam …
Explainable Optimal Random Forest model with conversational interface
HS Jennath, S Asharaf - Engineering Applications of Artificial Intelligence, 2025 - Elsevier
Abstract Machine Learning (ML) models are now a part of our everyday lives and
significantly impact each individual. When users are given a clear and relevant explanation …
significantly impact each individual. When users are given a clear and relevant explanation …
Bilingual spam sms detection using machine learning
Every day, Bangladeshis receive several SMS spam messages on their phones in both
Bangla and English text. Spam is defined as unsolicited bulk communications in a variety of …
Bangla and English text. Spam is defined as unsolicited bulk communications in a variety of …
NeuroDAVIS: A neural network model for data visualization
The task of dimensionality reduction and visualization of high-dimensional datasets remains
a challenging problem since long. Modern high-throughput technologies produce large …
a challenging problem since long. Modern high-throughput technologies produce large …
Convergence Behavior of an Adversarial Weak Supervision Method
Labeling data via rules-of-thumb and minimal label supervision is central to Weak
Supervision, a paradigm subsuming subareas of machine learning such as crowdsourced …
Supervision, a paradigm subsuming subareas of machine learning such as crowdsourced …