Discriminative restricted Boltzmann machine for invariant pattern recognition with linear transformations

• A novel model TIClassRBM is proposed to achieve invariant pattern recognition.
• Three types of transformation in images are incorporated into ClassRBM.
• Probabilistic max-pooling is adopted to learn invariant representation.
• Label vector is connected to the units that extract invariant representations.
• Experiments on MNIST and NORB datasets show the effectiveness of TIClassRBM.

How to make a machine automatically achieve invariant pattern recognition like human brain is still very challenging in machine learning community. In this paper, we present a single hidden-layer network TIClassRBM for invariant pattern recognition by incorporating linear transformations into discriminative restricted Boltzmann machine. In our model, invariant feature extraction and pattern classification can be implemented simultaneously. The mapping from input features to class label is represented by two groups of weights: transformed weights that connect hidden units to data, and pooling weights that connect pooling units yielded by probabilistic max-pooling to class label. All weights play an important role in the invariant pattern recognition. Moreover, TIClassRBM can handle general transformations contained in images, such as translation, rotation and scaling. The experimental studies on the variations of MNIST and NORB datasets demonstrate that the proposed model yields the best performance among some comparative models.