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

<table>FVDS (one-LO-net architecture): comparing output from L-net 1 and variable <svg height="7.1624999" id="M188" style="vertical-align:-0.11285pt" version="1.1" viewbox="0 0 8.7250004 7.1624999" width="8.7250004" xmlns="http://www.w3.org/2000/svg">
<g transform="matrix(1.25,0,0,-1.25,0,7.1625)">
<g transform="translate(72,-66.27)">
<text transform="matrix(1,0,0,-1,-71.95,66.44)">
<tspan style="font-size: 12.50px; " x="0" y="0">𝑥</tspan>
</text>
</g>
</g>
</svg>.</table>

Journal of Robotics

fig12

Figure 12

Figure 12: Discovering and Characterizing Hidden Variables Using a Novel Neural Network Architecture: LO-Net 