On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks.
Sunil ThulasidasanGopinath ChennupatiJeff A. BilmesTanmoy BhattacharyaSarah MichalakPublished in: NeurIPS (2019)
Keyphrases
- neural network
- training process
- training algorithm
- neural network training
- feed forward neural networks
- multi layer perceptron
- pattern recognition
- feedforward neural networks
- back propagation
- training set
- artificial neural networks
- fuzzy logic
- backpropagation algorithm
- error back propagation
- training patterns
- camera calibration
- recurrent neural networks
- feed forward
- supervised learning
- recurrent networks
- genetic algorithm
- training phase
- neural nets
- training samples
- hidden layer
- activation function
- stereo camera
- fuzzy systems
- camera parameters
- deep learning
- pose estimation
- semi supervised
- neural network structure
- deep architectures
- bayesian networks
- hand eye coordination