Jul 27, 2013

Facial Expression Recognition Challenge

By the way, I managed to get the first public result with nnForge: The 3rd place in Challenges in Representation Learning: Facial Expression Recognition Challenge at Kaggle.

This contest and two others were the base for the ICML 2013 Workshop on Challenges in Representation Learning, all the results are well covered and analyzed in "Challenges in Representation Learning: A report on three machine learning contests", Ian Goodfellow et al, arXiv:1307.0414.

nnForge v1.0.5

Just published nnForge v1.0.5:
  • Regularization "Upper bound on L2 norm of the incoming weight vector for each output neuron" added
  • ROC-type result now works fine for multi-class output types
  • rotate_band data and noise_data_transformer transformers added
  • Dropout is now done per input neuron instead of per input feature map - more robust option
  • Minor fixes