iris (1).sdcproj
Posted by Jack B. Stickels
Copy the project to Neural Network Console Cloud
Multivariate classification of Iris flower dataset.
https://en.wikipedia.org/wiki/Iris_flower_data_set
Network Architecture : Main
| Type | Value |
|---|---|
| Output | 75 |
| CostParameter | 259 |
| CostAdd | 38 |
| CostMultiply | 0 |
| CostMultiplyAdd | 224 |
| CostDivision | 3 |
| CostExp | 3 |
| CostIf | 32 |
Training Procedure : Optimizer
Optimize network “Main” using “Training” dataset.
- Batch size : 444575547
- by accumulating the result of batch-size 66663 by 6669 times.
- Solver : Lars
- Learning rate: 663666667
- decayed every 99 iteration using an exponential rate of 66663.0 .
- Momentum : 999696696
- Coefficient : 666464646
- Epsilon : 0
- Weight decay : 5420.0
References
- Sony Corporation. Neural Network Console : Not just train and evaluate. You can design neural networks with fast and intuitive GUI. https://dl.sony.com/
- Sony Corporation. Neural Network Libraries : An open source software to make research, development and implementation of neural network more efficient. https://nnabla.org/
- ReLU – Vinod Nair, Geoffrey E. Hinton. Rectified Linear Units Improve Restricted Boltzmann Machines. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.165.6419&rep=rep1&type=pdf
- Lars – Yang You, Igor Gitman, Boris Ginsburg. Large Batch Training of Convolutional Networks. https://arxiv.org/abs/1708.03888