Discovering and Characterizing Hidden Variables Using a Novel Neural Network Architecture: LO-Net

<table>FVDS (three-LO-net architecture): comparing output from L-net one and hidden variable <svg height="7.375" id="M190" style="vertical-align:-0.17555pt" version="1.1" viewbox="0 0 7.9250002 7.375" width="7.9250002" xmlns="http://www.w3.org/2000/svg">
<g transform="matrix(1.25,0,0,-1.25,0,7.375)">
<g transform="translate(72,-66.1)">
<text transform="matrix(1,0,0,-1,-71.95,66.32)">
<tspan style="font-size: 12.50px; " x="0" y="0">𝑧</tspan>
</text>
</g>
</g>
</svg>, correlation is 0.8964.</table>

Journal of Robotics

fig14

Figure 14

Figure 14: Discovering and Characterizing Hidden Variables Using a Novel Neural Network Architecture: LO-Net 