7 papers
Learning What to Remember: Adaptive Probabilistic Memory Retention for Memory-Efficient Language Models
S M Rafiuddin, Muntaha Nujat Khan
Transformer attention scales quadratically with sequence length O(n^2), limiting long-context use. We propose Adaptive Retention, a probabilistic, layer-wise token selection mechan…
High Cursive Complex Character Recognition using GAN External Classifier
S M Rafiuddin
Handwritten characters can be trickier to classify due to their complex and cursive nature compared to simple and non-cursive characters. We present an external classifier along wi…
Isolated Bangla Handwritten Character Classification using Transfer Learning
Abdul Karim, S M Rafiuddin, Jahidul Islam Razin +1
Bangla language consists of fifty distinct characters and many compound characters. Several notable studies have been performed to recognize Bangla characters, both handwritten and…
A Long Short-Term Memory (LSTM) Model for Business Sentiment Analysis Based on Recurrent Neural Network
Md. Jahidul Islam Razin, Md. Abdul Karim, M. F. Mridha +2
Business sentiment analysis (BSA) is one of the significant and popular topics of natural language processing. It is one kind of sentiment analysis techniques for business purposes…
Estimation of Phylogenetic Tree using Gene Sequencing Data
S M Rafiuddin
A phylogenetic tree is an important way in Bioinformatics to find the evolutionary relationship among biological species. In this research, a proposed model is described for the es…
Ranking of Bangla Word Graph using Graph-based Ranking Algorithms
S M Rafiuddin
Ranking words is an important way to summarize a text or to retrieve information. A word graph is a way to represent the words of a sentence or a text as the vertices of a graph an…