# The Fractal Geometry of Nature

##### Citations

20,028 citations

18,415 citations

11,357 citations

8,091 citations

### Cites background or methods from "The Fractal Geometry of Nature"

...Mandelbrot’s (1982) modification of Zipf’s law introduces a third parameter v, asserting that the probabilities are given by...

[...]

...) In the limit of large but otherwise standard networks, Neal (1996) has shown that the prior distribution over nonlinear functions implied by the Bayesian neural network falls in a class of probability distributions known as Gaussian processes....

[...]

...) In the limit of large but otherwise standard networks, Neal (1996) has shown that the prior distribution over nonlinear functions implied by the Bayesian neural network falls in a class of probability distributions known as Gaussian processes. The hyperparameters of the neural network model determine the characteristic lengthscales of the Gaussian process. Neal’s observation motivates the idea of discarding parameterized networks and working directly with Gaussian processes. Computations in which the parameters of the network are optimized are then replaced by simple matrix operations using the covariance matrix of the Gaussian process. In this chapter I will review work on this idea by Williams and Rasmussen (1996), Neal (1997b), Barber and Williams (1997) and Gibbs and MacKay (2000), and will assess whether, for supervised regression and classification tasks, the feedforward network has been superceded....

[...]

7,412 citations

### Cites background from "The Fractal Geometry of Nature"

...In fact, the LeH vy #ight trajectory can be assigned a fractal dimension d f "k [38,42,89] and is commonly supposed to be an e$cient search strategy of living organisms [141,142,146]....

[...]

##### References

16,554 citations

6,513 citations

5,087 citations