Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Cinquin, Tristan"'
Laplace approximations are popular techniques for endowing deep networks with epistemic uncertainty estimates as they can be applied without altering the predictions of the neural network, and they scale to large models and datasets. While the choice
Externí odkaz:
http://arxiv.org/abs/2407.13711
Autor:
Cinquin, Tristan, Bamler, Robert
Bayesian neural networks (BNN) promise to combine the predictive performance of neural networks with principled uncertainty modeling important for safety-critical systems and decision making. However, posterior uncertainty estimates depend on the cho
Externí odkaz:
http://arxiv.org/abs/2406.04317
Gradient boosting machines (GBMs) based on decision trees consistently demonstrate state-of-the-art results on regression and classification tasks with tabular data, often outperforming deep neural networks. However, these models do not provide well-
Externí odkaz:
http://arxiv.org/abs/2302.10706
In recent years, the transformer has established itself as a workhorse in many applications ranging from natural language processing to reinforcement learning. Similarly, Bayesian deep learning has become the gold-standard for uncertainty estimation
Externí odkaz:
http://arxiv.org/abs/2110.04020