The architecture challenge: Future artificial-intelligence systems will require sophisticated architectures, and knowledge of the brain might guide their construction

In this commentary, we highlight a crucial challenge posed by the proposal of Lake et al. to introduce key elements of human cognition into deep neural networks and future artificial-intelligence systems: the need to design effective sophisticated architectures. We propose that looking at the brain is an important means of facing this great challenge.

[1]  Andreea C. Bostan,et al.  Consensus Paper: Towards a Systems-Level View of Cerebellar Function: the Interplay Between Cerebellum, Basal Ganglia, and Cortex , 2016, The Cerebellum.

[2]  James L. McClelland,et al.  Autonomous Mental Development by Robots and Animals , 2001, Science.

[3]  Matthew T. Kaufman,et al.  Neural population dynamics during reaching , 2012, Nature.

[4]  Bernhard Sendhoff,et al.  Creating Brain-Like Intelligence , 2009, Creating Brain-Like Intelligence.

[5]  Michael L. Anderson.  Embodied Cognition: A field guide , 2003, Artif. Intell..

[6]  K. Gurney,et al.  The nucleus accumbens as a nexus between values and goals in goal-directed behavior: a review and a new hypothesis , 2013, Front. Behav. Neurosci..

[7]  D. Parisi,et al.  TRoPICALS: a computational embodied neuroscience model of compatibility effects. , 2010, Psychological review.

[8]  Francesco Mannella,et al.  The roles of the amygdala in the affective regulation of body, brain, and behaviour , 2010, Connect. Sci..

[9]  A. Graybiel.  The basal ganglia: learning new tricks and loving it , 2005, Current Opinion in Neurobiology.

[10]  Mitsuo Kawato,et al.  Cerebellar supervised learning revisited: biophysical modeling and degrees-of-freedom control , 2011, Current Opinion in Neurobiology.

[11]  D. Wolpert,et al.  Internal models in the cerebellum , 1998, Trends in Cognitive Sciences.

[12]  Douglas L. Jones,et al.  From motivation to action: Functional interface between the limbic system and the motor system , 1980, Progress in Neurobiology.

[13]  M. Goodale,et al.  The visual brain in action , 1995 .

[14]  Joshua B. Tenenbaum,et al.  Building machines that learn and think like people , 2016, Behavioral and Brain Sciences.

[15]  Francesco Mannella,et al.  Selection of cortical dynamics for motor behaviour by the basal ganglia , 2015, Biological Cybernetics.

[16]  Kenji Doya,et al.  What are the computations of the cerebellum, the basal ganglia and the cerebral cortex? , 1999, Neural Networks.

[17]  Stan Franklin,et al.  A Foundational Architecture for Artificial General Intelligence , 2007, AGI.

[18]  Francesco Mannella,et al.  The Hierarchical Organisation of Cortical and Basal-Ganglia Systems: A Computationally-Informed Review and Integrated Hypothesis , 2013, Computational and Robotic Models of the Hierarchical Organization of Behavior.

[19]  Gianluca Baldassarre,et al.  What are intrinsic motivations? A biological perspective , 2011, 2011 IEEE International Conference on Development and Learning (ICDL).

[20]  Rolf Pfeifer,et al.  Morphological Computation - Connecting Brain, Body, and Environment , 2006, Australian Conference on Artificial Intelligence.

[21]  Marco Mirolli,et al.  Intrinsically Motivated Learning in Natural and Artificial Systems , 2013 .

[22]  A. Barto,et al.  Intrinsic motivations and open-ended development in animals, humans, and robots: an overview , 2014, Front. Psychol..

[23]  Francesco Mannella,et al.  Intrinsically motivated action-outcome learning and goal-based action recall: a system-level bio-constrained computational model. , 2013, Neural networks : the official journal of the International Neural Network Society.

[24]  J. Krakauer,et al.  A computational neuroanatomy for motor control , 2008, Experimental Brain Research.

[25]  Marco Mirolli,et al.  GRAIL: A Goal-Discovering Robotic Architecture for Intrinsically-Motivated Learning , 2016, IEEE Transactions on Cognitive and Developmental Systems.

[26]  S. Scott.  Optimal feedback control and the neural basis of volitional motor control , 2004, Nature Reviews Neuroscience.

[27]  Joel L. Davis,et al.  A Model of How the Basal Ganglia Generate and Use Neural Signals That Predict Reinforcement , 1994 .

[28]  J. Lisman,et al.  The Hippocampal-VTA Loop: Controlling the Entry of Information into Long-Term Memory , 2005, Neuron.

[29]  Joel L. Davis,et al.  Adaptive Critics and the Basal Ganglia , 1995 .

[30]  V. Penhune,et al.  Author's Personal Copy Behavioural Brain Research Parallel Contributions of Cerebellar, Striatal and M1 Mechanisms to Motor Sequence Learning , 2022 .