A new search for two-neutrino double-beta ($2\nu\beta\beta$) decay of $^{136}\rm Xe$ to the $0^+_1$ excited state of $^{136}\rm Ba$ is performed with the full EXO-200 dataset. A deep learning-based convolutional neural network is used to discriminate signal from background events. Signal detection efficiency is increased relative to previous searches by EXO-200 by more than a factor of two. With the addition of the Phase II dataset taken with an upgraded detector, the median 90$\%$ confidence level half-life sensitivity of $2\nu\beta\beta$ decay to the $0^+_1$ state of $^{136}\rm Ba$ is $2.9 \times 10^{24}~\rm yr$ using a total $^{136}\rm Xe$ exposure of $234.1~\rm kg~yr$. No statistically significant evidence for $2\nu\beta\beta$ decay to the $0^+_1$ state is observed, leading to a lower limit of $T^{2\nu}_{1/2}(0^+ \rightarrow 0^+_1) > 1.4\times10^{24}~\rm yr$ at 90$\%$ confidence level, improved by 70$\%$ relative to the current world's best constraint.
Comment: 9 pages, 7 figures, 2 tables