Input Transformation and Output Combination for Improved Handwritten Digit Recognition
2015
Recent Neural Network Architectures with a deep and complex structure and that rely on ensemble averaging have led to an improvement in isolated handwritten digit recognition. Here a specific set of input pattern transformations is presented that achieves good results with modestly sized Neural Networks. Using some heuristics for the construction of an ensemble allows reaching low error rates.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
24
References
2
Citations
NaN
KQI