Probabilistic Interpretation of Feedforward Network Outputs, with Relationships to Statistical Prediction of Ordinal Quantities

@article{Costa1996ProbabilisticIO,
  title={Probabilistic Interpretation of Feedforward Network Outputs, with Relationships to Statistical Prediction of Ordinal Quantities},
  author={Mario Costa},
  journal={International journal of neural systems},
  year={1996},
  volume={7 5},
  pages={
          627-37
        }
}
  • Mario Costa
  • Published 1996
  • Mathematics, Computer Science, Medicine
  • International journal of neural systems
Several problems require the estimation of discrete random variables whose values can be put in a one-to-one ordered correspondence with a finite subset of the natural numbers. This happens whenever quantities are involved that represent integer items, or have been quantized on a fixed number of levels, or correspond to "graded" linguistic values. Here we propose a correct probabilistic approach to such kind of problems that fully exploits all the available prior knowledge about their own… Expand
Classification of Ordinal Data Using Neural Networks
The unimodal model for the classification of ordinal data
Ordinal Neural Networks Without Iterative Tuning
Ordinal regression neural networks based on concentric hyperspheres
A snapshot on nonstandard supervised learning problems
A snapshot on nonstandard supervised learning problems: taxonomy, relationships, problem transformations and algorithm adaptations
A snapshot on nonstandard supervised learning problems: taxonomy, relationships and methods
Classification of Ordinal Data
Attention-based Encoder-Decoder Networks for Spelling and Grammatical Error Correction
...
1
2
...

References

SHOWING 1-10 OF 21 REFERENCES
Probabilistic neural networks
Low power, low voltage conductance-mode CMOS analog neuron
Analog VLSI implementation of neural networks
  • E. Vittoz
  • Computer Science
  • IEEE International Symposium on Circuits and Systems
  • 1990
and E
  • Pasero
  • 1995
Analog VLSI implementation of Neural Networks
and Y
  • LeCun
  • 1991
\Low p o w er, low v oltage conductancemode CMOS analog neuron
  • Proc. V International Conference on Microelectronics for Neural Networks and Fuzzy Systems (MicroNeuro '96). Lausanne (CH)
  • 1996
...
1
2
3
...