This talk will be about the differences between Artificial Neural Networks (ANNs) and Biological Neural Networks (BNNs). ANNs refer to a computing system, the fundamental composition of which is analogous to biological neural networks. As ANNs are a sparse but efficient representation of BNNs, there exist a lot of differences. The primary differences between ANNs and BNNs are rooted in network topology. Differences in network configuration, information processing, and energetic efficiency are all governed to an extent by network topology. Specifically, we provide a number of specific distinctions between ANNs and BNNs: representational complexity, topological complexity, and the role of network topology in energy consumption. One overarching theme of this talk is how ANNs can benefit from heterogeneity in network topology by including features such as functional modules, biologically realistic learning rules, and "rich club" connectivity.