All models discussed in the paper use ReLU non-linearity.

They are 300 Poisson neurons, where the first 100 encode the whisker stimulus, the next 100 encode the auditory cue and the last 100 act as an extra noise source for our model. Out of the 300 neurons, 60 of them are inhibitory (red). The input neurons project unrestrictedly to the whole RSNN. The baseline firing rate of all input neurons is 5 Hz. The whisker stimulus and auditory cue are encoded with an increase of the firing rate for 10 ms, starting 4 ms after the onset of the actual stimuli.

Probabilistic modelling lies at the heart of machine learning.

We introduce a probability distribution, combined with an efficient sampling algorithm, for weights and biases of fully-connected neural networks.

Neural operators [Kovachki et al., 2021a,b] are neural networks that take a

A neural network (cf. Figure 1) can be thought of as a directed acyclic network consisting of

The Appendix is structured as follows: We provide a proof of conditional guarantees in EENNs for (hard) PoE in Appendix A . We conduct an ablation study for our P A model in Appendix B.2 . We report results of NLP experiments in Appendix B.4 . We discuss anytime regression and deep ensembles in Appendix B.6 . We propose a technique for controlling the violations of conditional monotonicity in P A in Appendix B.8 .