Sensorimotor in Space and Time: Audition

Processing complex temporal sequences is still challenging since existing frameworks are handcrafted (e.g., the cascaded structure of the convolutional neural networks (CNNs)) for each specific problem. Their parameters need to be finely tuned for each specific problem because they use the symbolic representations. In this work, we propose the new Developmental Network 2 (DN-2) to overcome these challenges. The DN-2 uses patterns as representations and shows strengths in conducting abstraction from concrete sensory examples. We present a new theory about how hidden regions emerge, including the number, boundaries, and connections. We designed, implemented, and tested this new network and used the phoneme recognition experiment as an example of audition modality. Based on the experimental results, we analyzed both the advantages of the new mechanisms in DN-2 and how these new mechanisms help DN-2 to automatically generate a hierarchical architecture. We believe DN-2 is in the right direction of dealing with various sequential data. This work is the first step for our goal of auditory-language autonomous learning.

[1]  Juyang Weng,et al.  Synapse maintenance in the Where-What Networks , 2011, The 2011 International Joint Conference on Neural Networks.

[2]  S. Wanska,et al.  The relationship of spatial concept development to the acquisition of locative understanding. , 1984, The Journal of genetic psychology.

[3]  Mitchell Glickstein.  How are visual areas of the brain connected to motor areas for the sensory guidance of movement? , 2000, Trends in Neurosciences.

[4]  Juyang Weng,et al.  Information-dense actions as contexts , 2018, Neurocomputing.

[5]  J. Knott.  The organization of behavior: A neuropsychological theory , 1951 .

[6]  Y. Dan,et al.  Spike timing-dependent plasticity: a Hebbian learning rule. , 2008, Annual review of neuroscience.

[7]  M. Scanziani,et al.  Instantaneous Modulation of Gamma Oscillation Frequency by Balancing Excitation with Inhibition , 2009, Neuron.

[8]  J. Piaget,et al.  The Origins of Intelligence in Children , 1971 .

[9]  M. Goldberg,et al.  Neuronal Activity in the Lateral Intraparietal Area and Spatial Attention , 2003, Science.

[10]  Juyang Weng,et al.  Brain as an Emergent Finite Automaton: A Theory and Three Theorems , 2015 .

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

[12]  G. F. Hughes,et al.  On the mean accuracy of statistical pattern recognizers , 1968, IEEE Trans. Inf. Theory.

[13]  Andrew W. Senior,et al.  Long short-term memory recurrent neural network architectures for large scale acoustic modeling , 2014, INTERSPEECH.

[14]  A. Campbell.  Histological Studies on the Localisation of Cerebral Function , 2009 .

[15]  L. Vygotsky.  Mind in Society: The Development of Higher Psychological Processes: Harvard University Press , 1978 .

[16]  H. Chugani.  A critical period of brain development: studies of cerebral glucose utilization with PET. , 1998, Preventive medicine.

[17]  L. S. Vygotskiĭ,et al.  Mind in society : the development of higher psychological processes , 1978 .

[18]  D. Fry.  Homo Loquens: Man as a Talking Animal , 1977 .

[19]  Juyang Weng,et al.  Cross-domain and within-domain synaptic maintenance for autonomous development of visual areas , 2015, 2015 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob).

[20]  Juyang Weng,et al.  Symbolic Models and Emergent Models: A Review , 2012, IEEE Transactions on Autonomous Mental Development.

[21]  A. Thiele,et al.  Attention – oscillations and neuropharmacology , 2009, The European journal of neuroscience.