main webpage
W Topic
Computer Science
arXiv (Cornell University)
Fine-Tuning Language Models via Epistemic Neural Networks
2022
Language models often pre-train on large unsupervised text corpora, then fine-tune on additional task-specific data. However, typical fine-tuning schemes do not prioritize the examples that they tune on. We show that, if you can prioritize informative trainin…
Article

Computer Science

Study of computation

Computer science is the study of computation, information, and automation. Computer science spans theoretical disciplines (such as algorithms, theory of computation, and information theory) to applied disciplines (including the design and implementation of hardware and software).

Algorithms and data structures are central to computer science. The theory of computation concerns abstract models of computation and general classes of problems that can be solved using them. The fields of cryptography and computer security involve studying the means for secure communication and preventing security vulnerabilities. Computer graphics and computational geometry address the generation of images.

Exploring foci of:
arXiv (Cornell University)
Fine-Tuning Language Models via Epistemic Neural Networks
2022
Language models often pre-train on large unsupervised text corpora, then fine-tune on additional task-specific data. However, typical fine-tuning schemes do not prioritize the examples that they tune on. We show that, if you can prioritize informative training data, you can achieve better performance while using fewer labels. To do this we augment a language model with an epinet: a small additional network that helps to estimate model uncertainty and forms an \textit{epistemic neural network} (ENN). ENNs are neura…
Click Computer Science Vs:
Artificial Intelligence
Heuristic
Machine Learning
Deep Learning
Generative Grammar
Training, Validation, And Test Data Sets
Management
Economics