The field of neural networks is moving towards more biologically inspired architectures, with a focus on improving robustness, efficiency, and brain-like features. Recent research has shown that incorporating topographic constraints, hierarchical processing, and spiking neural networks can lead to more robust and efficient models. These advancements have the potential to address long-standing challenges in machine learning, such as data inefficiency and vulnerability to adversarial perturbations. Notable papers in this area include: VCNet, which introduces a novel neural network architecture informed by the macro-scale organization of the primate visual cortex, achieving state-of-the-art results on specialized benchmarks. TDSNNs, which proposes a spatio-temporal constraints loss function for topographic deep spiking neural networks, successfully replicating the hierarchical spatial functional organization observed in the primate visual cortex.