Artificial neural networks (ANNs) are computational models that are loosely inspired by their biological counterparts. In recent years, major breakthroughs in ANN research have transformed the machine learning landscape from an engineering perspective. At the same time, scientists have started to revisit ANNs ...
Artificial neural networks (ANNs) are computational models that are loosely inspired by their biological counterparts. In recent years, major breakthroughs in ANN research have transformed the machine learning landscape from an engineering perspective. At the same time, scientists have started to revisit ANNs as models of neural information processing in biological agents. From an empirical point of view, neuroscientists have shown that ANNs provide state-of-the-art predictions of neural responses to naturalistic stimuli. From a theoretical point of view, computational neuroscientists have started to address the foundations of learning and inference in next-generation ANNs, identifying the desiderata that models of neural information processing should fulfill.
The goal of this Research Topic is to bring together key experimental and theoretical ANN research with the aim of providing new insights on information processing in biological neural networks through the use of artificial neural networks. We welcome contributions that are of direct relevance to neuroscientists that use ANNs as a model of neural information processing. This topic is timely given the recent exciting developments in the field and will be highly attractive to a wide community of brain researchers, as well as for the community at large.
Keywords:
artificial neural networks, deep learning, neural information processing
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.