Artificial neural networks (ANN) were conceived as computational systems inspired by the structure and functioning of the human brain. These networks were designed to solve complex problems by learning from data, trying to emulate the way biological neurons process information. In recent years, several models that introduce more bioinspired properties into artificial neural networks have appeared. Among these models we can include Artificial Metaplasticity, KLN (Konio Cortex Like) networks, or Competitive Perceptrons (CPs). Metaplasticity is an advanced concept in neuroscience and Deep learning that refers to the ability of a neural networks to modify its own synaptic plasticity, that is: metaplasticity would be the plasticity of plasticity. In the context of biological neural networks, metaplasticity is key for learning and memory processes. Some important bioinspired features in metaplasticity include Synaptic homeostasis which allow neural networks to maintain a balance between plasticity and stability. And the concepts of LTP (Long-Term Potentiation) and LTD (Long-Term Depression) which describe how synapses between neurons strengthen or weaken in response to neuronal activity, and are essential for neural biological processes. Metaplasticity has been successfully implemented in both supervised and unsupervised neural networks in models such as Artificial Metaplasticity Multilayer Perceptron (AMMLP) or Artificial Metaplasticity Self Organization Map (AMSOM) adjusting learning rates in a more adaptive and bioinspired way. KLN-type neural networks (Koniocortex-Like Networks) are an emerging approach inspired by the architecture and functions of the brain’s koniocortex. The koniocortex is a cortical region that includes primary sensory areas, such as the primary visual cortex, primary auditory cortex, and primary somatosensory cortex. KLN networks seek to replicate the hierarchical connectivity and organization patterns of the koniocortex. They implement feedback and recursion mechanisms to improve the precision and stability of processing, emulating biological cortical circuits. Finally, Competitive Perceptrons are unsupervised learning artificial neural networks in which nodes compete for the right to respond to a subset of the input data. A variant of Hebbian learning, competitive learning works by increasing the specialization of each node in the network. Competition occurs naturally due to inhibition between neurons; when one activates, it inhibits others the winning neuron emerges in a dynamic process based in lateral inhibition between neurons.