We state concentration inequalities for the output of the hidden layers of a stochastic deep neural network (SDNN), as well as for the output of the whole SDNN. These results allow us to introduce an expected classifier (EC), and to give probabilistic upper bound for the classification error of the EC. We also state the optimal number of layers for the SDNN via an optimal stopping procedure. We apply our analysis to a stochastic version of a feedforward neural network with ReLU activation function.
31 December 2022 in Involve, a Journal of Mathematics
We present two classes of abstract prearithmetics, and . The first one is weakly projective with respect to the nonnegative real Diophantine arithmetic , and the second one is projective with respect to the extended real Diophantine arithmetic . In addition, we have that every and every is a complete totally ordered semiring. We show that the projection of any series of elements of converges in , for any , and that the projection of any non-indeterminate series of elements of converges in , for all . We also prove that working in , for any , and in , for all , allows to overcome a version of the paradox of the heap.
We formulate an ergodic theory for the (almost sure) limit $\mathcal{P}^\text{co}_{\tilde{\mathcal{E}}}$ of a sequence $(\mathcal{P}^\text{co}_{\mathcal{E}_n})$ of successive dynamic imprecise probability kinematics (DIPK, introduced in Caprio and Gong, 2021) updates of a set $\mathcal{P}^\text{co}_{\mathcal{E}_0}$ representing the initial beliefs of an agent. As a consequence, we formulate a strong law of large numbers.