8 papers
Few-Shot Bioactivity Prediction with Meta-Learning under Assay Heterogeneity
Michal Kmicikiewicz, Tommy Rochussen, Vincent Fortuin +1
Accurate bioactivity prediction is a central challenge in early-stage drug discovery, as individual assays often contain too few measurements to train reliable models independently…
Decision-Aligned Evaluation of Uncertainty Quantification
Annika Schneider, Tommy Rochussen, Joshua Stiller +1
Uncertainty estimates in machine learning are typically evaluated using generic metrics such as the negative log-likelihood and expected calibration error, yet good performance on…
Amortising Inference and Meta-Learning Priors in Neural Networks
Tommy Rochussen, Vincent Fortuin
One of the core facets of Bayesianism is in the updating of prior beliefs in light of new evidenceso how can we maintain a Bayesian approach if we have no prior belief…
Incremental Transformer Neural Processes
Philip Mortimer, Cristiana Diaconu, Tommy Rochussen +2
Neural Processes (NPs), and specifically Transformer Neural Processes (TNPs), have demonstrated remarkable performance across tasks ranging from spatiotemporal forecasting to tabul…
Sparse Gaussian Neural Processes
Tommy Rochussen, Vincent Fortuin
Despite significant recent advances in probabilistic meta-learning, it is common for practitioners to avoid using deep learning models due to a comparative lack of interpretability…
Structured Partial Stochasticity in Bayesian Neural Networks
Tommy Rochussen
Bayesian neural network posterior distributions have a great number of modes that correspond to the same network function. The abundance of such modes can make it difficult for app…
Amortised Inference in Neural Networks for Small-Scale Probabilistic Meta-Learning
Matthew Ashman, Tommy Rochussen, Adrian Weller
The global inducing point variational approximation for BNNs is based on using a set of inducing inputs to construct a series of conditional distributions that accurately approxima…
Amortised Inference in Bayesian Neural Networks
Tommy Rochussen
Meta-learning is a framework in which machine learning models train over a set of datasets in order to produce predictions on new datasets at test time. Probabilistic meta-learning…