We, at HyperMatrix, work towards developing trustworthy and responsible AI. The current focus is on the robustness, generalization, interpretation and explainability of deep learning models. The lab is led by Professor Hassan Sajjad at the Faculty of Computer Science, Dalhousie University.
- We will be at ACL 2023. Check out our presentations on:
1) Impact of Adversarial Training on Robustness and Generalizability of Language Models,
2) Neuron-level Interpretation of Deep NLP Models: A Survey,
3) NeuroX Library for Neuron Analysis of Deep NLP Models
- ICLR 2023: Learning Uncertainty for Unknown Domains with Zero-Target-Assumption
- Talk by Hassan: Latent Concepts in Transformer Models of NLP. UKP, TU Darmstadt, Germany (Jun. 2023)