In computational networks, the activation function of a node defines the output of that node given an input or set of inputs. A standard computer… (More)

Semantic Scholar uses AI to extract papers important to this topic.

2016

2016

- Çaglar Gülçehre, Marcin Moczulski, Misha Denil, Yoshua Bengio
- ICML
- 2016

† University of Oxford Abstract Common activation functions used in neural networks can yield to training difficulties due to the… (More)

Is this relevant?

Highly Cited

2010

Highly Cited

2010

- Zhigang Zeng, Tingwen Huang, Wei Xing Zheng
- IEEE Transactions on Neural Networks
- 2010

In this brief, stability of multiple equilibria of recurrent neural networks with time-varying delays and the piecewise linear… (More)

Is this relevant?

Highly Cited

2008

Highly Cited

2008

- Qingshan Liu, Jun Wang
- IEEE Transactions on Neural Networks
- 2008

In this paper, a one-layer recurrent neural network with a discontinuous hard-limiting activation function is proposed for… (More)

Is this relevant?

Highly Cited

2004

Highly Cited

2004

This paper investigates the absolute exponential stability of a general class of delayed neural networks, which require the… (More)

Is this relevant?

Highly Cited

1998

Highly Cited

1998

- Lorenzo Vecci, Francesco Piazza, Aurelio Uncini
- Neural Networks
- 1998

In this paper, we study the theoretical properties of a new kind of artificial neural network, which is able to adapt its… (More)

Is this relevant?

Highly Cited

1995

Highly Cited

1995

- Tianping Chen, Hong Chen
- IEEE Trans. Neural Networks
- 1995

The purpose of this paper is to investigate neural network capability systematically. The main results are: 1) every Tauber… (More)

Is this relevant?

Highly Cited

1995

Highly Cited

1995

- Tianping Chen, Hong Chen
- IEEE Trans. Neural Networks
- 1995

The purpose of this paper is to explore the representation capability of radial basis function (RBF) neural networks. The main… (More)

Is this relevant?

Highly Cited

1993

Highly Cited

1993

- Moshe Leshno, Vladimir Ya. Lin, Allan Pinkus, Shimon Schocken
- Neural Networks
- 1993

-Several researchers characterized the activation fimction under which multilayer feedforward networks can act as universal… (More)

Is this relevant?

Highly Cited

1991

Highly Cited

1991

- Kurt Hornik
- Neural Networks
- 1991

-We show that standard multilayer feedfbrward networks with as few as a single hidden layer and arbitrary bounded and nonconstant… (More)

Is this relevant?

Highly Cited

1989

Highly Cited

1989

- M. C. Stinchcombe, Hannah Jean White
- International 1989 Joint Conference on Neural…
- 1989

K.M. Hornik, M. Stinchcombe, and H. White (Univ. of California at San Diego, Dept. of Economics Discussion Paper, June 1988; to… (More)

Is this relevant?