Context-modulation of hippocampal dynamics and deep convolutional networks

Complex architectures of biological neural circuits, such as parallel processing pathways, has been behaviorally implicated in many cognitive studies. However, the theoretical consequences of circuit complexity on neural computation have only been explored in limited cases. Here, we introduce a mechanism by which direct and indirect pathways from cortex to the CA3 region of the hippocampus can balance both contextual gating of memory formation and driving network activity. We implement this concept in a deep artificial neural network by enabling a context-sensitive bias. The motivation for this is to improve performance of a size-constrained network. Using direct knowledge of the superclass information in the CIFAR-100 and Fashion-MNIST datasets, we show a dramatic increase in performance without an increase in network size.

[1]  E T Rolls,et al.  Computational constraints suggest the need for two distinct input systems to the hippocampal CA3 network , 1992, Hippocampus.

[2]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[3]  Mark J. Schnitzer,et al.  Impermanence of dendritic spines in live adult CA1 hippocampus , 2015, Nature.

[4]  F. Gage,et al.  Resolving New Memories: A Critical Look at the Dentate Gyrus, Adult Neurogenesis, and Pattern Separation , 2011, Neuron.

[5]  Ila R Fiete,et al.  What Grid Cells Convey about Rat Location , 2008, The Journal of Neuroscience.

[6]  D. J. Felleman,et al.  Distributed hierarchical processing in the primate cerebral cortex. , 1991, Cerebral cortex.

[7]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

[9]  G. Buzsáki,et al.  Single granule cells reliably discharge targets in the hippocampal CA3 network in vivo , 2002, Nature Neuroscience.

[10]  Ojas Parekh,et al.  A Combinatorial Model for Dentate Gyrus Sparse Coding , 2017, Neural Computation.

[11]  Christophe Mulle,et al.  Operation and plasticity of hippocampal CA3 circuits: implications for memory encoding , 2017, Nature Reviews Neuroscience.

[12]  Matthew D. Zeiler.  ADADELTA: An Adaptive Learning Rate Method , 2012, ArXiv.

[13]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .