… neuroscience research in the age of deeplearning. We discuss the conceptual and methodological challenges of comparing behaviour, learning … have emerged for neuroscience as …
… neuroscientists can use deeplearning in their work, from inspiring theories to serving as full computational models. Ongoing advances in deeplearning … core of cognitive neuroscience. …
H Tanaka, A Nayebi… - Advances in neural …, 2019 - proceedings.neurips.cc
… We build on ideas from interpretable machinelearning, notably methods of input attribution that can decompose a neural response into a sum of contributions either from individual …
… in PFC, with the goal of enhancing the synergy between neuroscience and machinelearning. … various functions, with an eye toward principles that may be transferable to deeplearning. …
MW Mathis, A Mathis - Current opinion in neurobiology, 2020 - Elsevier
… However, there are no animal-specific toolboxes geared towardsneuroscience applications, although we believe that this will change in the near future, as for many applications having …
… literature on the application of deeplearning to the clinical neurosciences. We used search … and challenges inherent in the deeplearning approaches adopted towards these tasks, as …
… towards achieving this goal, and highlight important issues and predictions for neuroscience … optimize functionality while remaining truthful to neuroscience findings. As in any theoretical …
AJE Kell, JH McDermott - Current opinion in neurobiology, 2019 - Elsevier
… Here we review applications of deeplearning to sensory neuroscience, discussing potential limitations and future directions. We highlight the potential uses of deepneuralnetworks to …
P Rupprecht, S Carta, A Hoffmann, M Echizen… - … Neuroscience, 2021 - nature.com
… a deep convolutional network Several favorable properties make supervised deeplearning … First, deeplearning generally tends to outperform other classification or regression methods …