31 citations · 31 across the 2 of their papers we have counts for
3 papers
cs.LG2024
Calibrating Where It Matters: Constrained Temperature Scaling
Stephen McKenna, Jacob Carse
We consider calibration of convolutional classifiers for diagnostic decision making. Clinical decision makers can use calibrated classifiers to minimise expected costs given their…
cs.CV2021
Unsupervised Representation Learning from Pathology Images with Multi-directional Contrastive Predictive Coding
Jacob Carse, Frank Carey, Stephen McKenna
Digital pathology tasks have benefited greatly from modern deep learning algorithms. However, their need for large quantities of annotated data has been identified as a key challen…
cs.AI2016★ 31 cited
Deep Reinforcement Learning for Multi-Domain Dialogue Systems
Heriberto Cuayáhuitl, Seunghak Yu, Ashley Williamson +1
Standard deep reinforcement learning methods such as Deep Q-Networks (DQN) for multiple tasks (domains) face scalability problems. We propose a method for multi-domain dialogue pol…