Research Article
A New Generalized Deep Learning Framework Combining Sparse Autoencoder and Taguchi Method for Novel Data Classification and Processing
Table 21
A comparison of handwritten digit classification results.
| Referance | Methods | Accuracy % |
| Anupama Kaushik et al. [36] | J48 | 70.0 | Anupama Kaushik et al. [36] | NaiveBayes | 72.65 | Anupama Kaushik et al. [36] | SMO | 89.95 | Olarik Surinta et al. [37] | Hotspot + SVM | 92.70 | U Ravi Babu et al. [38] | Hotspot + k-NN | 96.94 | Hinton GE et al. [39] | Deep Belief Network | 98.75 | LeCun Y et al. [40] | Deep Conv. Net LeNet-5 | 99.05 | Wan L [41] | Deep Conv. Net (dropconnect) | 99.43 | Zelier MD [42] | Deep Conv. Net (stochastic pooling) | 99.53 | Goodfellow IJ [43] | Deep Conv. Net (maxout units and dropout) | 99.55 | Lee CY [44] | Deep Conv. Net (deeply-supervised) | 99.61 | Proposed Framework | Deep Autoencoder based on Taguchi Method | 99.80 |
|
|