[HTML][HTML] Accuracy assessment in convolutional neural network-based deep learning remote sensing studies—Part 1: Literature review
Convolutional neural network (CNN)-based deep learning (DL) is a powerful, recently
developed image classification approach. With origins in the computer vision and image …
developed image classification approach. With origins in the computer vision and image …
[HTML][HTML] A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications
Data scarcity is a major challenge when training deep learning (DL) models. DL demands a
large amount of data to achieve exceptional performance. Unfortunately, many applications …
large amount of data to achieve exceptional performance. Unfortunately, many applications …
Using deepspeed and megatron to train megatron-turing nlg 530b, a large-scale generative language model
Pretrained general-purpose language models can achieve state-of-the-art accuracies in
various natural language processing domains by adapting to downstream tasks via zero …
various natural language processing domains by adapting to downstream tasks via zero …
Teaching models to express their uncertainty in words
We show that a GPT-3 model can learn to express uncertainty about its own answers in
natural language--without use of model logits. When given a question, the model generates …
natural language--without use of model logits. When given a question, the model generates …
Improving calibration for long-tailed recognition
Deep neural networks may perform poorly when training datasets are heavily class-
imbalanced. Recently, two-stage methods decouple representation learning and classifier …
imbalanced. Recently, two-stage methods decouple representation learning and classifier …
Evidential deep learning for open set action recognition
In a real-world scenario, human actions are typically out of the distribution from training data,
which requires a model to both recognize the known actions and reject the unknown …
which requires a model to both recognize the known actions and reject the unknown …
Uncertainty in natural language processing: Sources, quantification, and applications
As a main field of artificial intelligence, natural language processing (NLP) has achieved
remarkable success via deep neural networks. Plenty of NLP tasks have been addressed in …
remarkable success via deep neural networks. Plenty of NLP tasks have been addressed in …
Rethinking calibration of deep neural networks: Do not be afraid of overconfidence
Capturing accurate uncertainty quantification of the prediction from deep neural networks is
important in many real-world decision-making applications. A reliable predictor is expected …
important in many real-world decision-making applications. A reliable predictor is expected …
[HTML][HTML] Antibody structure prediction using interpretable deep learning
Therapeutic antibodies make up a rapidly growing segment of the biologics market.
However, rational design of antibodies is hindered by reliance on experimental methods for …
However, rational design of antibodies is hindered by reliance on experimental methods for …
Dynamically weighted balanced loss: class imbalanced learning and confidence calibration of deep neural networks
KRM Fernando, CP Tsokos - IEEE Transactions on Neural …, 2021 - ieeexplore.ieee.org
Imbalanced class distribution is an inherent problem in many real-world classification tasks
where the minority class is the class of interest. Many conventional statistical and machine …
where the minority class is the class of interest. Many conventional statistical and machine …