A Joint Optimization of Momentum Item and Levenberg-Marquardt Algorithm to Level Up the BPNN’s Generalization Ability

<table class="table-group" width="800px"><tr class="fig-image" id="a"><td><img alt="653072.fig.009a" src="https://static.hindawi.com/articles/mpe/volume-2014/653072/figures/653072.fig.009a.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(a) </b>ELM-BPNN</td></tr></table></td></tr><tr class="fig-image" id="b"><td><img alt="653072.fig.009b" src="https://static.hindawi.com/articles/mpe/volume-2014/653072/figures/653072.fig.009b.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(b) </b>NLM-BPNN</td></tr></table></td></tr><tr class="fig-image" id="c"><td><img alt="653072.fig.009c" src="https://static.hindawi.com/articles/mpe/volume-2014/653072/figures/653072.fig.009c.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(c) </b>Proposed LM-BPNN</td></tr></table></td></tr></table>

<table>Classification errors in 2D of wine data.</table>

Mathematical Problems in Engineering

fig9

Figure 9

Figure 9: A Joint Optimization of Momentum Item and Levenberg-Marquardt Algorithm to Level Up the BPNN’s Generalization Ability 