NLP Course | Home Works | Fall 2021 | Dr. Behrooz Minaei

MOCA-Net: Novel neural architecture with sparse MoE, external memory, and budget-aware computation. Real Stanford SST-2 integration, O(L) complexity, 96.40% accuracy. Built for efficient sequence modeling.

A meta-learning system that predicts when a sentiment transformer is about to be wrong

PerceptNet: A controlled comparison of sparse linear perceptrons and embedding-based MLPs for text classification on SST-2 sentiment and 20 Newsgroups topic tasks.

BERT-based sentiment analysis for IMDB and SST-2 datasets using Hugging Face Transformers. Includes training, evaluation, and batch prediction scripts under MIT License.