论文标题
机器学习光超颈椎
Machine learning light hypernuclei
论文作者
论文摘要
我们采用馈送人造神经网络在大型空间中推断出{\ it ab-initio}的结果$λ$分离能量的超核无核壳模型计算最轻的超努力的$b_λ$最轻的hypernuclei，$^3_λ$ h，$^3_λ$ h，$^4_λ$ h和$^4_λ$ h和$^4_λ$ HE，可在计算机上获得计算机，核子核子，核子核子核子和核核子相互作用。通过扩大输入数据集的大小并在神经网络的训练过程中引入高斯噪声来避免过度拟合的问题。我们发现，具有八个神经元的一个隐藏层的网络足以正确推断$λ$分离能的值，以建模大小$ n_ {max} = 100 $的空间。获得的结果与实验数据一致，如果$^3_λ$ H和$ 0^+$的$^4_λ$ HE的状态，尽管它们的实验不超过$ 0.3 $ MEV的$ 0^+$和$ 1^+$ $ 1^+$的状态，$^4_λ$ H和$ 1^+$ 1^+$^+$^$^$^4__λ$ He He He He。我们发现，我们的结果与使用无核壳模型计算的其他外推方案获得的结果非常吻合，这表明ANN是推断高核无核壳模型计算结果到大型模型空间的可靠方法。
We employ a feed-forward artificial neural network to extrapolate at large model spaces the results of {\it ab-initio} hypernuclear No-Core Shell Model calculations for the $Λ$ separation energy $B_Λ$ of the lightest hypernuclei, $^3_Λ$H, $^4_Λ$H and $^4_Λ$He, obtained in computationally accessible harmonic oscillator basis spaces using chiral nucleon-nucleon, nucleon-nucleon-nucleon and hyperon-nucleon interactions. The overfitting problem is avoided by enlarging the size of the input dataset and by introducing a Gaussian noise during the training process of the neural network. We find that a network with a single hidden layer of eight neurons is sufficient to extrapolate correctly the value of the $Λ$ separation energy to model spaces of size $N_{max}=100$. The results obtained are in agreement with the experimental data in the case of $^3_Λ$H and the $0^+$ state of $^4_Λ$He, although they are off of the experiment by about $0.3$ MeV for both the $0^+$ and $1^+$states of $^4_Λ$H and the $1^+$ state of $^4_Λ$He. We find that our results are in excellent agreement with those obtained using other extrapolation schemes of the No-Core Shell Model calculations, showing this that an ANN is a reliable method to extrapolate the results of hypernuclear No-Core Shell Model calculations to large model spaces.
