Philip Woodland
5 papers · 2018–2024 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(12)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
model compression
(1)
bayesian inference
(1)
uncertainty quantification
(1)
epistemic uncertainty
(1)
speech recognition
(1)
emotion recognition
(1)
natural gradient
(1)
parameter sharing
(1)
natural gradient descent
(1)
fisher information matrix
(1)
gaussian mixture model
(1)
long short-term memory
(1)
deep neural network
(1)
pre-trained model
(1)
parameter-efficient fine-tuning
(1)
uncertainty estimation
(1)
aleatoric uncertainty
(1)
adaptive training
(1)
gating mechanism
(1)
joint optimization
(1)
Papers
An Improved Empirical Fisher Approximation for Natural Gradient Descent
NeurIPS 2024
Estimating the Uncertainty in Emotion Attributes using Deep Evidential Regression
ACL 2023
Combining Natural Gradient with Hessian Free Methods for Sequence Training
Interspeech 2018
Semi-tied Units for Efficient Gating in LSTM and Highway Networks
Interspeech 2018
Speaker Adaptation and Adaptive Training for Jointly Optimised Tandem Systems
Interspeech 2018