Derivative-free prompt learning has emerged as a lightweight alternative to prompt tuning,
which only requires model inference to optimize the prompts. However, existing work did not …

Ensembling BERT models often significantly improves accuracy, but at the cost of
significantly more computation and memory footprint. In this work, we propose Multi-CLS …

Recent studies on deep ensembles have identified the sharpness of the local minima of
individual learners and the diversity of the ensemble members as key factors in improving …

Selective prediction aims to learn a reliable model that abstains from making predictions
when uncertain. These predictions can then be deferred to humans for further evaluation. As …

The advanced models of deep neural networks like bidirectional encoder from the
transformers (BERT) and others, poses challenges in terms of computational resources and …

Deep learning has achieved remarkable success in various domains, including computer
vision, natural language processing, and game playing. However, this success relies on the …

Artificial Neural Networks are state-of-the-art machine learning models, outperforming their
competitors in many fields. One of the major drawbacks of Artificial Neural Networks are the …

Breast cancer represents 25% of all new cancer cases and is the second leading cause of
death from cancer in Canadian women. The preferred treatment for breast cancer patients is …

Recently, researchers have found that transformer-based language models (LMs), such as
GPT-2, can predict the next word distribution better as their sizes grow [177, 21, 97] …