# Information dynamics based self-adaptive reservoir for delay temporal memory tasks

- 464 Downloads
- 17 Citations

## Abstract

Recurrent neural networks of the reservoir computing (RC) type have been found useful in various time-series processing tasks with inherent non-linearity and requirements of variable temporal memory. Specifically for delayed response tasks involving the transient memorization of information (temporal memory), self-adaptation in RC is crucial for generalization to varying delays. In this work using information theory, we combine a generalized intrinsic plasticity rule with a local information dynamics based schema of reservoir neuron leak adaptation. This allows the RC network to be optimized in a self-adaptive manner with minimal parameter tuning. Local active information storage, measured as the degree of influence of previous activity on the next time step activity of a neuron, is used to modify its leak-rate. This results in RC network with non-uniform leak rate which depends on the time scales of the incoming input. Intrinsic plasticity (IP) is aimed at maximizing the mutual information between each neuron’s input and output while maintaining a mean level of activity (homeostasis). Experimental results on two standard benchmark tasks confirm the extended performance of this system as compared to the static RC (fixed leak and no IP) and RC with only IP. In addition, using both a simulated wheeled robot and a more complex physical hexapod robot, we demonstrate the ability of the system to achieve long temporal memory for solving a basic T-shaped maze navigation task with varying delay time scale.

## Keywords

Recurrent neural networks Self-adaptation Information theory Intrinsic plasticity Temporal memory## Notes

### Acknowledgments

The research leading to these results has received funding from the Emmy Noether Program DFG, MA4464/3-1, by the European Communitys Seventh Framework Programme FP7/2007-2013 (Specific Programme Cooperation, Theme3, Information and Communication Technologies) under grant agreement no.270273, Xperience, by the Federal Ministry of Education and Research(BMBF) by grants to the Bernstein Center for Computational Neuroscience (BCCN) Göttingen, grant number 01GQ1005A, project D1 and by the Max Planck Research School for Physics of Biological and Complex Systems.

## References

- Antonelo E, Schrauwen B, Stroobandt D (2008) Mobile robot control in the road sign problem using reservoir computing networks. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pp 911–916Google Scholar
- Bertschinger N, Natschläger T (2004) Real-time computation at the edge of chaos in recurrent neural networks. Neural Comput 16:1413–1436CrossRefMATHGoogle Scholar
- Bernacchia A, Seo H, Lee D, Wang XJ (2011) A reservoir of time constants for memory traces in cortical neurons. Nat Neurosci 14(3):366–372CrossRefGoogle Scholar
- Boedecker J, Obst O, Mayer MN, Asada M (2009) Initialization and self-organized optimization of recurrent neural network connectivity. HFSP J 5:340–349CrossRefGoogle Scholar
- Buonomano DV, Laje R (2010) Population clocks: motor timing with neural dynamics. Trends Cogn Sci 14:520–527CrossRefGoogle Scholar
- Büsing L, Schrauwen B, Legenstein R (2010) Connectivity, dynamics, and memory in reservoir computing with binary and analog neurons. Neural Comput 22:1272–1311MathSciNetCrossRefMATHGoogle Scholar
- Desai NS, Rutherford LC, Turrigiano GG (1999) Plasticity in the intrinsic excitability of cortical pyramidal neurons. Nat Neurosci 2:515–520CrossRefGoogle Scholar
- Ganguli S, Dongsung H, Sompolinsky H (2008) Memory traces in dynamical systems. Proc Natl Acad Sci USA 105:18970–18975CrossRefGoogle Scholar
- Jaeger H (2001) Short term memory in echo state networks. GMD Report 152, German National Research Center for Information TechnologyGoogle Scholar
- Jaeger H (2003) Adaptive nonlinear system identification with echo state networks. In: Advances in Neural Information Processing Systems, pp 593–600Google Scholar
- Jaeger H, Haas H (2004) Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 2:78–80CrossRefGoogle Scholar
- Jaeger H, Lukosevicius M, Popovici D, Siewert U (2007) Optimization and applications of echo state networks with leaky-integrator neurons. Neural Netw 20:335–352CrossRefMATHGoogle Scholar
- Jaeger H (2007) Discovering multiscale dynamical features with hierarchical echo state networks (Tech. Rep. No. 10). Jacobs University, BremenGoogle Scholar
- Li C (2011) A model of neuronal intrinsic plasticity. IEEE Trans Auton Ment Dev 3:277–284CrossRefGoogle Scholar
- Lizier TJ, Pritam M, Prokopenko M (2011) Information dynamics in small-world boolean networks. Artif Life 17:293–314CrossRefGoogle Scholar
- Lizier JT (2012) JIDT: an information-theoretic toolkit for studying the dynamics of complex systems. http://code.google.com/p/information-dynamics-toolkit/
- Lizier TJ, Prokopenko M, Zomaya AY (2012) Local measures of information storage in complex distributed computation. Inf Sci 208:39–54CrossRefGoogle Scholar
- Lukosevicius M, Jaeger H (2009) Reservoir computing approaches to recurrent neural network training. Comput Sci Rev 3:127–149CrossRefGoogle Scholar
- Maass W, Natschläger T, Markram H (2004) Computational models for generic cortical microcircuits. In: Computational neuroscience: a comprehensive approach, chapter 18, pp 575–605Google Scholar
- Manoonpong P, Kolodziejski C, Wörgötter F, Morimoto J (2013a) Combining correlation-based and reward-based learning in neural control for policy improvement. Adv Complex Syst (in press)Google Scholar
- Manoonpong P, Parlitz U, Wörgötter F (2013b) Neural control and adaptive neural forward models for insect-like, energy-efficient, and adaptable locomotion of walking machines. Front Neural Circuits 7:12. doi: 10.3389/fncir.2013.00012 CrossRefGoogle Scholar
- Ozturk MC, Xu D, Prncipe JC (2007) Analysis and design of echo state networks. Neural Comput 19:111–138CrossRefMATHGoogle Scholar
- Paleologu C, Benesty J, Ciochino S (2008) A robust variable forgetting factor recursive least-squares algorithm for system identification. IEEE Signal Process Lett 15:597–600CrossRefGoogle Scholar
- Ren G, Chen W, Kolodziejski C, Wörgötter F, Dasgupta S, Manoonpong P (2012) Multiple chaotic central pattern generators for locomotion generation and leg damage compensation in a hexapod robot. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp 2756–2761Google Scholar
- Schrauwen B, Wardermann M, Verstraeten D, Steil JJ, Stroobandt D (2008) Improving reservoirs using intrinsic plasticity. Neurocomputing 71:1159–1171CrossRefGoogle Scholar
- Shi Z, Han M (2007) Support vector echo-state machine for chaotic time-series prediction. IEEE Trans Neural Netw 18:359–372CrossRefGoogle Scholar
- Sompolinsky H, Crisanti A, Sommers HJ (1988) Chaos in random neural networks. Phys Rev Lett 61:259–262MathSciNetCrossRefGoogle Scholar
- Steingrube S, Timme M, Wörgötter F, Manoonpong P (2010) Self-organized adaptation of a simple neural circuit enables complex robot behaviour. Nat Phys 6:224–230CrossRefGoogle Scholar
- Sussillo D, Abbott LF (2009) Generating coherent patterns of activity from chaotic neural networks. Neuron 4:544–557CrossRefGoogle Scholar
- Tetzlaff C, Kolodziejski C, Markelic I, Wörgötter F (2012) Time scales of memory, learning, and plasticity. Biol Cybern 6:715–26CrossRefGoogle Scholar
- Triesch J (2007) Synergies between intrinsic and synaptic plasticity mechanisms. Neural Comput 4:885–909MathSciNetCrossRefGoogle Scholar
- Turrigiano G, Abbott LF, Marder E (1994) Activity-dependent changes in the intrinsic properties of cultured neurons. Science 264:974–977CrossRefGoogle Scholar
- Ungerleider LG, Courtney SM, Haxby JV (1998) A neural system for human visual working memory. Proc Natl Acad Sci USA 95:883–890CrossRefGoogle Scholar
- Yamashita Y, Tani J (2008) Emergence of Functional hierarchy in a multiple timescale neural network model: a humanoid robot experiment. PLoS Comput Biol 4(11):e1000220. doi: 10.1371/journal.pcbi.1000220