Search Results for author:
Found 13 papers, 3 papers with code
Finetuning Language Models to Emit Linguistic Expressions of Uncertainty
In this work, we explore supervised finetuning on uncertainty-augmented predictions as a method to develop models that produce linguistic expressions of uncertainty.
Towards Responsible Development of Generative AI for Education: An Evaluation-Driven Approach
A major challenge facing the world is the provision of equitable and universal access to quality education.
Is forgetting less a good inductive bias for forward transfer?
We argue that the measure of forward transfer to a task should not be affected by the restrictions placed on the continual learner in order to preserve knowledge of previous tasks.
Architecture Matters in Continual Learning
However, in this work, we show that the choice of architecture can significantly impact the continual learning performance, and different architectures lead to different trade-offs between the ability to remember previous tasks and learning new ones.
One Pass ImageNet
We present the One Pass ImageNet (OPIN) problem, which aims to study the effectiveness of deep learning in a streaming setting.
Wide Neural Networks Forget Less Catastrophically
A primary focus area in continual learning research is alleviating the "catastrophic forgetting" problem in neural networks by designing new algorithms that are more robust to the distribution shifts.
Linear Mode Connectivity in Multitask and Continual Learning
Continual (sequential) training and multitask (simultaneous) training are often attempting to solve the same overall objective: to find a solution that performs well on all considered tasks.
A maximum-entropy approach to off-policy evaluation in average-reward MDPs
This work focuses on off-policy evaluation (OPE) with function approximation in infinite-horizon undiscounted Markov decision processes (MDPs).
Hybrid Models with Deep and Invertible Features
We propose a neural hybrid model consisting of a linear model defined on a set of features computed by a deep, invertible transformation (i. e. a normalizing flow).
Do Deep Generative Models Know What They Don't Know?
A neural network deployed in the wild may be asked to make predictions for inputs that were drawn from a different distribution than that of the training data.
Indian Buffet Processes with Power-law Behavior
The Indian buffet process (IBP) is an exchangeable distribution over binary matrices used in Bayesian nonparametric featural models.
Dependent Dirichlet Process Spike Sorting
In this paper we propose a new incremental spike sorting model that automatically eliminates refractory period violations, accounts for action potential waveform drift, and can handle appearance" and "disappearance" of neurons.
An Efficient Sequential Monte Carlo Algorithm for Coalescent Clustering
We propose an efficient sequential Monte Carlo inference scheme for the recently proposed coalescent clustering model (Teh et al, 2008).
