READ ME File For 'Data for "Identification of spatial intensity profiles from femtosecond laser machined depth profiles via neural networks"'

Dataset DOI: 10.5258/SOTON/D1934

ReadMe Author: Michael. D. T. McDonnell, University of Southampton

This dataset supports the publication:
AUTHORS: M.D.T.MCDONNELL, J. A. GRANT-JACOB, M. PRAEGER, R. W.EASON, and B. MILLS
TITLE: Identification of spatial intensity profiles from femtosecond laser machined depth profiles via neural networks
JOURNAL: Optics Express



This dataset contains: All figures used in the publication
The figures are as follows:

Figure 1: Experimental schematic.

Figure 2: Figure design description.

Figure 3: Block structure for the:
		a) Generator
		b) Discriminator

Figure 4: Losses used:
		a) Discriminator Loss
		b) Comparative loss
		c) Cycle consistent loss

Figure 5: The process for creating and testing the trained NN-generated DMD profiles:
		a) From experimental results
		b) From a desired depth profile

Figure 6: Comparison of a traditional GAN and the novel GAN.

Figure 7: Neural network varience:
		a) Three pulses and a corresponding experimental depth profile
		b-d) Three predictions from the primary network

Figure 8: Three example DMD sequences generated from a single depth profile with inputweightings defined

Figure 9: Using the weighting input of the network to control the temporal position ofwhite pixels in the sequence of DMD patterns.

Figure 10: Three example DMD sequences generated from a single depth profile withinput weightings defined as:
		a) [0, 0, 1]
		b) [1, 0, 0]
		c) [1/6, 1/3, 1/2]

Figure 11: Generating sequences of DMD patterns to machine a specified depth profile.



Date of data collection: 20/11/2019 - 14/04/2021

Information about geographic location of data collection: Data was collected at the University of Southampton, Building 46 (Physics)

Licence:CC-BY

Related projects:
Engineering and Physical Sciences Research Council (EPSRC) (EP/N03368X/1).

Date that the file was created: 24/08/2021