S. T. Claus1, Y. Eti2, and E. S. Terbuny3
1Dept. of Presents, North Pole Research Agency, Rovaniemi, Finland, 2Atopof Amountain, Himalaya, Bhutan, 3Dept. for Sweets, Greenfield Institute, Ostereistedt, Germany
Synopsis
Detecting Easter bunnies is a task that is difficult to impossible for humans - thus, the use of artificial intelligence is more than warranted. In this work we present a confounded nut-work noisette (CNN) algorithm based on extended, accelerated systematic tracking in
experimental radiology with encephalo-graphic generation (EASTER-EGG). Using this method we demonstrate that chocolate is a volatile resource especially when hungry researchers are present.
Introduction
Detection and tracking of legendary animals and
subjects such as Big Foot, the Yeti, Santa Claus and others has so far only
been realized with ancient and outdated methods including optical viewing or
bear traps. These methods do neither use artificial intelligence nor magnetic
resonance imaging, and are therefore inherently inferior which is also demonstrated
by the low number of publications in this field [1]. In this work we propose a
new method based on extended, accelerated systematic tracking in experimental
radiology with encephalo-graphic generation (EASTER-EGG), which uses
non-straight (off course) MRI and artificially incremented (AI) confounded
nut-work noisette (CNN) algorithms to detect, extract, harvest and finally
digest the mythical Easter bunny from a background of cocoa-shelled spherical
objects (CSSO)[2].Materials and Methods
EASTER-EGG data were
acquired using an unbelievably timid echo (UTE) sequence with its signature
Rabbit Feigning (RF) pulse shape (Fig. 1) to lure the subject into the hare
cage of an open bore magnet. The dissipated RF power in the bait was limited to
0.001 Watts·rung [2] to avoid pre-mature phase changes
in the CSSOs [3]. The experiment was approved by the local IRB (Nr.:
I8U-E*-2020). Phantom preparation was performed by a trained plastic surgeon
with more than 4 years of eating experience with forks and knives (Fig. 2).
After
image acquisition the hyper-dimensional data were Fourier-transmogrified, and
the phantom material was thrown to the floor to be analysed manually by several
unfortunate volunteers (ground truth). Then, a completely nutty net ($$$CNN$$$, [4]) with the
convoluted nut-work noisette (CNN) algorithm was trained on photographs of
cute kittens that we downloaded from the internet to search for whatever was
left over. The CNN
[4a] is essentially based on a greedy downslope
head-over-heals method with some really important modifications that we have
carefully hidden in our obfuscated code (not to be found on github
[5]). MR images (Fig. 3) were then projected onto television sets (POTS) and
were shown to the CNN to
prove the superiority of AI in general. Results
The CNN being a $$$CNN$$$ with CNN did not
like the input data which was taken as a clear sign for the overwhelming
intelligence of the algorithm. Based on our prior experience with MRI with
virtually no data [6] we concluded that no further experiments were necessary.
The measurements could not have been repeated anyway due to the sparse seasonal
appearance of this mythical creature [7] and the sudden disappearance at the
end of the experiment [8].Conclusion
AI is the best method to detect Easter bunnies
when it is combined with MRI. For a wide-spread application massive research
funding programs must be initiated to develop low-cost portable MRI systems for
garden use. The methods presented in this work might also be applied to
underwater imaging at Loch Ness using the earth’s magnetic field.Acknowledgements
This work was supported by the Lost & Found
Foundation under grant number UR2GRT. Only non-alcoholic acronym finders were
employed.References
[1] N. Othing: Why AI has to be in it! BiggerData (2021), -1:3,14-9,77.
[2] T. Turner: What’s chocolate got to do with it? Parlophone (1993)
[3] M. Elting, et al. RF cooking with chocolate is not a good
idea. Magn Reson Cook (2019) 17: 1
[4] Note the use of the different
font!
[4a] We are using yet another font
here to simplify the notation.
[5] G. Ollum. My precious – why you will never get it. Lord of the Rings (Mordor
Press)
[6] K. Space. High-frequency data is highly overrated: be mean with only one point at
k=0. Small Data Gazette (1973)
[7] J. Hennig. E*-Bunnies—how to find, recognize, use or avoid them. Mythical MRI
(1891) 0:0-0
[8] D. Scully, F. Moulder. Sudden chocolate disappearences explained:
theobromine traces lead the way. Extra Files (1985) X: xx-xx