Inferring Motor Programs from Images of Handwritten Digits

We describe a generative model for handwritten digits that uses two pairs of opposing springs whose stiffnesses are controlled by a motor program. We show how neural networks can be trained to infer the motor programs required to accurately reconstruct the MNIST digits. The inferred motor programs can be used directly for digit classification, but they can also be used in other ways. By adding noise to the motor program inferred from an MNIST image we can generate a large set of very different images of the same class, thus enlarging the training set available to other methods. We can also use the motor programs as additional, highly informative outputs which reduce overfitting when training a feed-forward classifier.

[1]  D. Mackay MINDLIKE BEHAVIOUR IN ARTEFACTS* , 1951, The British Journal for the Philosophy of Science.

[2]  D. Mackay Mind-Like Behaviour in Artefacts , 1951 .

[3]  Murray Eden,et al.  Handwriting and pattern recognition , 1962, IRE Trans. Inf. Theory.

[4]  Robert A. Jacobs,et al.  Increased rates of convergence through learning rate adaptation , 1987, Neural Networks.

[5]  W. J. Holmes,et al.  Extension of the bandwidth of the JSRU parallel-formant synthesizer for high quality synthesis of male and female speech , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[6]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[7]  M. Hallet,et al.  Speech Recognition: A Model and a Program for Research* , 1998 .

[8]  Geoffrey E. Hinton,et al.  Recognizing Hand-written Digits Using Hierarchical Products of Experts , 2002, NIPS.

[9]  Patrice Y. Simard,et al.  Best practices for convolutional neural networks applied to visual document analysis , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[10]  Bernhard Schölkopf,et al.  Training Invariant Support Vector Machines , 2002, Machine Learning.

[11]  J. Hollerbach An oscillation theory of handwriting , 2004, Biological Cybernetics.