NLP Course | Home Works | Fall 2021 | Dr. Behrooz Minaei
BERT-based sentiment analysis for IMDB and SST-2 datasets using Hugging Face Transformers. Includes training, evaluation, and batch prediction scripts under MIT License.
PerceptNet: A controlled comparison of sparse linear perceptrons and embedding-based MLPs for text classification on SST-2 sentiment and 20 Newsgroups topic tasks.
A meta-learning system that predicts when a sentiment transformer is about to be wrong
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.
grep for waveforms — read signal values, clock frequency, and transitions from Synopsys FSDB, Cadence SST2, and open VCD dumps, straight from the shell. Deterministic output, runs locally, no viewer. CLI + MCP server + Claude Code skill.
End-to-end ONNX quantization benchmark for DistilBERT — FP32 vs dynamic vs static INT8, comparing accuracy, latency, and model size tradeoffs
To associate your repository with the sst2 topic, visit your repo's landing page and select "manage topics."