How to study the neural mechanisms of multiple tasks

Most biological and artificial neural systems are capable of completing multiple tasks. However, the neural mechanism by which multiple tasks are accomplished within the same system is largely unclear. We start by discussing how different tasks can be related, and methods to generate large sets of inter-related tasks to study how neural networks and animals perform multiple tasks. We then argue that there are mechanisms that emphasize either specialization or flexibility. We will review two such neural mechanisms underlying multiple tasks at the neuronal level (modularity and mixed selectivity), and discuss how different mechanisms can emerge depending on training methods in neural networks.

[1]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[2]  Rich Caruana,et al.  Multitask Learning , 1998, Encyclopedia of Machine Learning and Data Mining.

[3]  Michael W. Cole,et al.  The task novelty paradox: Flexible control of inflexible neural pathways during rapid instructed task learning , 2017, Neuroscience & Biobehavioral Reviews.

[4]  Danielle S Bassett,et al.  Effective learning is accompanied by high-dimensional and efficient representations of neural activity , 2017, Nature Neuroscience.

[5]  Xiao-Jing Wang,et al.  Internal Representation of Task Rules by Recurrent Dynamics: The Importance of the Diversity of Neural Responses , 2010, Front. Comput. Neurosci..

[6]  Jonathan D. Power,et al.  Multi-task connectivity reveals flexible hubs for adaptive task control , 2013, Nature Neuroscience.

[7]  Michael W. Cole,et al.  Conflict detection and resolution rely on a combination of common and distinct cognitive control networks , 2017, Neuroscience & Biobehavioral Reviews.

[8]  Li Fei-Fei,et al.  CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Walter Schneider,et al.  The Brain’s Learning and Control Architecture , 2012 .

[10]  Jane X. Wang,et al.  Reinforcement Learning, Fast and Slow , 2019, Trends in Cognitive Sciences.

[11]  Peter L. Bartlett,et al.  RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning , 2016, ArXiv.

[12]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[13]  N. Daw,et al.  Deciding How To Decide: Self-Control and Meta-Decision Making , 2015, Trends in Cognitive Sciences.

[14]  Stefano Fusi,et al.  Why neurons mix: high dimensionality for higher cognition , 2016, Current Opinion in Neurobiology.

[15]  Marco Baroni,et al.  Generalization without Systematicity: On the Compositional Skills of Sequence-to-Sequence Recurrent Networks , 2017, ICML.

[16]  Jesper Andersson,et al.  A multi-modal parcellation of human cerebral cortex , 2016, Nature.

[17]  Walter Schneider,et al.  Controlled and automatic human information processing: II. Perceptual learning, automatic attending and a general theory. , 1977 .

[18]  J. DiCarlo,et al.  Using goal-driven deep learning models to understand sensory cortex , 2016, Nature Neuroscience.

[19]  L. F. Abbott,et al.  Generating Coherent Patterns of Activity from Chaotic Neural Networks , 2009, Neuron.

[20]  Oriol Vinyals,et al.  Matching Networks for One Shot Learning , 2016, NIPS.

[21]  Christopher D. Harvey,et al.  Recurrent Network Models of Sequence Generation and Memory , 2016, Neuron.

[22]  Michael W. Cole,et al.  Prefrontal Dynamics Underlying Rapid Instructed Task Learning Reverse with Practice , 2010, The Journal of Neuroscience.

[23]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[24]  Stefano Fusi,et al.  Flexible coding of memory and space in the primate hippocampus during virtual navigation , 2018, bioRxiv.

[25]  Richard S. Zemel,et al.  Prototypical Networks for Few-shot Learning , 2017, NIPS.

[26]  J. Movshon,et al.  The analysis of visual motion: a comparison of neuronal and psychophysical performance , 1992, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[27]  Xiao-Jing Wang,et al.  Task representations in neural networks trained to perform many cognitive tasks , 2019, Nature Neuroscience.

[28]  Dmitriy Aronov,et al.  Mapping of a non-spatial dimension by the hippocampal/entorhinal circuit , 2017, Nature.

[29]  Hilla Peretz,et al.  The , 1966 .

[30]  Yuval Tassa,et al.  MuJoCo: A physics engine for model-based control , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[31]  W. Newsome,et al.  Context-dependent computation by recurrent dynamics in prefrontal cortex , 2013, Nature.

[32]  W. Schneider,et al.  Neuroimaging studies of practice-related change: fMRI and meta-analytic evidence of a domain-general control network for learning. , 2005, Brain research. Cognitive brain research.

[33]  Michael W. Cole,et al.  Rapid instructed task learning: A new window into the human brain’s unique capacity for flexible cognitive control , 2013, Cognitive, affective & behavioral neuroscience.

[34]  Walter Schneider,et al.  Controlled & automatic processing: behavior, theory, and biological mechanisms , 2003, Cogn. Sci..

[35]  Razvan Pascanu,et al.  Overcoming catastrophic forgetting in neural networks , 2016, Proceedings of the National Academy of Sciences.

[36]  Stefano Fusi,et al.  Computational principles of synaptic memory consolidation , 2016, Nature Neuroscience.

[37]  Surya Ganguli,et al.  Continual Learning Through Synaptic Intelligence , 2017, ICML.

[38]  Joshua B. Tenenbaum,et al.  Human-level concept learning through probabilistic program induction , 2015, Science.

[39]  Surya Ganguli,et al.  Cell types for our sense of location: where we are and where we are going , 2017, Nature Neuroscience.

[40]  Rich Caruana,et al.  Multitask Learning , 1997, Machine Learning.

[41]  Yee Whye Teh,et al.  Distral: Robust multitask reinforcement learning , 2017, NIPS.

[42]  Marcin Andrychowicz,et al.  One-Shot Imitation Learning , 2017, NIPS.

[43]  M. Botvinick,et al.  Conflict monitoring and cognitive control. , 2001, Psychological review.

[44]  Michael Cole,et al.  Cognitive task information is transferred between brain regions via resting-state network topology , 2017 .

[45]  Michael W. Cole,et al.  Mapping the human brain's cortical-subcortical functional network organization , 2018, NeuroImage.

[46]  Xiao-Jing Wang,et al.  A dataset and architecture for visual reasoning with a working memory , 2018, ECCV.

[47]  Ha Hong,et al.  Performance-optimized hierarchical models predict neural responses in higher visual cortex , 2014, Proceedings of the National Academy of Sciences.

[48]  R. Axel,et al.  A novel multigene family may encode odorant receptors: A molecular basis for odor recognition , 1991, Cell.

[49]  H. Harlow,et al.  The formation of learning sets. , 1949, Psychological review.

[50]  Selmaan N. Chettih,et al.  Dynamic Reorganization of Neuronal Activity Patterns in Parietal Cortex , 2017, Cell.

[51]  Zeb Kurth-Nelson,et al.  Learning to reinforcement learn , 2016, CogSci.

[52]  Jason Weston,et al.  Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks , 2015, ICLR.

[53]  David J. Freedman,et al.  Experience-dependent representation of visual categories in parietal cortex , 2006, Nature.

[54]  Guangyu R. Yang,et al.  Training Excitatory-Inhibitory Recurrent Neural Networks for Cognitive Tasks: A Simple and Flexible Framework , 2016, PLoS Comput. Biol..

[55]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[56]  Xiao-Jing Wang,et al.  Reward-based training of recurrent neural networks for cognitive and value-based tasks , 2016, bioRxiv.

[57]  Daniel L. K. Yamins,et al.  A Task-Optimized Neural Network Replicates Human Auditory Behavior, Predicts Brain Responses, and Reveals a Cortical Processing Hierarchy , 2018, Neuron.

[58]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[59]  Xiao-Jing Wang,et al.  The importance of mixed selectivity in complex cognitive tasks , 2013, Nature.

[60]  Christos Constantinidis,et al.  Stable population coding for working memory coexists with heterogeneous neural dynamics in prefrontal cortex , 2016, Proceedings of the National Academy of Sciences.

[61]  Nicolas Y. Masse,et al.  Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization , 2018, Proceedings of the National Academy of Sciences.

[62]  Matthias Bethge,et al.  The functional diversity of retinal ganglion cells in the mouse , 2015, Nature.

[63]  Michael W. Cole,et al.  Cognitive task information is transferred between brain regions via resting-state network topology , 2017, Nature Communications.

[64]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[65]  Wei Ji Ma,et al.  A diverse range of factors affect the nature of neural representations underlying short-term memory , 2018, Nature Neuroscience.

[66]  R. Masland The Neuronal Organization of the Retina , 2012, Neuron.

[67]  Doris Y. Tsao,et al.  A Cortical Region Consisting Entirely of Face-Selective Cells , 2006, Science.

[68]  Joel Z. Leibo,et al.  Prefrontal cortex as a meta-reinforcement learning system , 2018, bioRxiv.

[69]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[70]  Sebastian Ruder,et al.  An Overview of Multi-Task Learning in Deep Neural Networks , 2017, ArXiv.

[71]  David Badre,et al.  Frontal Cortex and the Hierarchical Control of Behavior , 2018, Trends in Cognitive Sciences.