Improving the Performance of Neural Networks in Regression Tasks Using Drawering

Prelegent(ci)

Konrad Żołna

Afiliacja

Uniwersytet Jagielloński

Termin

21 kwietnia 2017 15:30

Pokój

p. 5820

Seminarium

Seminarium badawcze Zakładu Logiki: Wnioskowania aproksymacyjne w eksploracji danych

---

The method presented extends a given regression neural network to make its performance improve. The modification affects the learning procedure only, hence the extension may be easily omitted during evaluation without any change in prediction. It means that the modified model may be evaluated as quickly as the original one but tends to perform better. This improvement is possible because the modification gives better expressive power, provides better behaved gradients and works as a regularization. The knowledge gained by the temporarily extended neural network is contained in the parameters shared with the original neural network. The only cost is an increase in learning time.

---