Information Technology Reference
In-Depth Information
We constructed the robot using a LEGO Mindstorms NXT toolkit and pro-
grammed the neural network using the RWTH Mindstorms NXT toolbox of
Matlab (which is freely available on the internet).
Despite the simplicity of the structure and the small number of neurons, the
robot is capable of continuous learning, that is, it learns during the execution of
its movements. In this way the robot learned what sequences of motor commands
lead him downwards and what sequences failed to do this.
For simulating the different stimuli that are present in Doman's inclined floor
technique, different stimuli were applied to the robotic structure. We performed
15 tests with each stimulus and calculate the average number of iterations it
takes for the robot to learn. According to our expectations and consistently to
Doman's empirical results, learning was quicker when more rewarding stimuli
were present. Our work also suggests some improvements for the inclined floor
technique that should be empirically tested.
References
1. Desai, N.S., Rutherford, L.C., Turrigiano, G.G.: Plasticity in the Intrinsic Ex-
citability of Cortical Pyramidal Neurons. Nature Neurosciences 2(6), 515-520
(1999)
2. Desai, N.: Homeostatic Plasticity in the CNS: Synaptic and Intrinsic Forms. Jour-
nal of Physiology 97, 391-402 (2003)
3. Doman, G.: What to do about your brain-injured child. In: Or your brain-damaged,
mentally retarded, mentally deficient, cerebral-palsied, emotionally disturbed, spas-
tic, flaccid, rigid, epileptic, autistic, athetoid, hyperactive, downs child. The Better
Baby Press, Philadelphia (1990)
4. Doman, G., Doman, D., Hagy, B.: How To Teach Your Baby To Be Physically
Superb: From Birth To Age Six; The Gentle Revolution. Square One Publishers
(2006)
5. Haykin, S.: Neural Networks: a comprehensive foundation. Prentice Hall, Inc.,
Englewood Cliffs (1999)
6. Hebb, D.O.: The organization of behaviour. Wiley, New York (1949)
7. Manabe, T., Shinoe, T., Matsui, M., Taketo, M.: Modulation of Synaptic Plasticity
by Physiological Activation of M1 Muscarinic Acetylcholine Receptors in the Mouse
Hippocampus. The Journal of Neuroscience 25(48), 11194-11200 (2005)
8. Pelaez, F.J.R., Simoes, M.G.: A computational model of synaptic metaplasticity.
In: Proceedings of the IJCNN 1999 International Joint Conference of Artificial
Neural Networks, Washington D.C (1999)
9. Pelaez, J.R., Piqueira, J.R.C.: Biological clues for up-to-date artificial neurons.
In: Andina, D., Phan, D.T. (eds.) Computational Inteligence: for Engineering and
Manufacturing, 1st edn., vol. 1, pp. 1-19. Springer-Verlag, Berlin (2006)
10. Takeda, N., Horii, A., Mochizuki, T., Okakura-Mochizuki, K., Yamatodani, A.:
Effects of vestibular stimulation on acetylcholine release from rat hippocampus: an
in vivo microdialysis study. Journal of Neurophysiology 72, 605-611 (1994)
11. Wiener, N.: Cybernetics: or control and communication in the animal and the
machine. MIT Press, Cambridge (1948)
Search WWH ::
Custom Search