模式识别与人工智能
模式識彆與人工智能
모식식별여인공지능
Moshi Shibie yu Rengong Zhineng
2015年
4期
354-360
,共7页
覆盖分类%流形%低维子空间%局部和全局映射(LGRM)
覆蓋分類%流形%低維子空間%跼部和全跼映射(LGRM)
복개분류%류형%저유자공간%국부화전국영사(LGRM)
Cover Classification%Manifold%Low-Dimensional Subspace%Local and Global Regressive Mapping (LGRM)
为探索高维数据本质结构和低维表示，并避免一般流形学习中测试数据不能显式降维的不足，提出基于局部和全局映射函数的流形降维空间球形覆盖分类算法。该算法首先抽象融合局部和全局信息映射模型，分别优化局部拉普拉斯矩阵和全局拉普拉斯矩阵，通过对局部和全局拉普拉斯矩阵进行特征值分解，得到训练样本的低维表示。然后借助核映射获取测试样本的低维表示。最后在低维空间建立球形覆盖分类模型，实现目标分类。在MNIST手写体数据集、YaleB和AR人脸数据集上的实验表明文中算法的有效性，证明其在实际应用领域具有一定价值。
為探索高維數據本質結構和低維錶示，併避免一般流形學習中測試數據不能顯式降維的不足，提齣基于跼部和全跼映射函數的流形降維空間毬形覆蓋分類算法。該算法首先抽象融閤跼部和全跼信息映射模型，分彆優化跼部拉普拉斯矩陣和全跼拉普拉斯矩陣，通過對跼部和全跼拉普拉斯矩陣進行特徵值分解，得到訓練樣本的低維錶示。然後藉助覈映射穫取測試樣本的低維錶示。最後在低維空間建立毬形覆蓋分類模型，實現目標分類。在MNIST手寫體數據集、YaleB和AR人臉數據集上的實驗錶明文中算法的有效性，證明其在實際應用領域具有一定價值。
위탐색고유수거본질결구화저유표시，병피면일반류형학습중측시수거불능현식강유적불족，제출기우국부화전국영사함수적류형강유공간구형복개분류산법。해산법수선추상융합국부화전국신식영사모형，분별우화국부랍보랍사구진화전국랍보랍사구진，통과대국부화전국랍보랍사구진진행특정치분해，득도훈련양본적저유표시。연후차조핵영사획취측시양본적저유표시。최후재저유공간건립구형복개분류모형，실현목표분류。재MNIST수사체수거집、YaleB화AR인검수거집상적실험표명문중산법적유효성，증명기재실제응용영역구유일정개치。
To explore the intrinsic structure and the low dimensional representation of high dimensional data and find explicit mapping in some manifold learning algorithms, spherical cover classification algorithm based on manifold dimension reduction space of local and global mapping is proposed. The mapping model combining local information and global information is extracted firstly. The local laplacian matrix and the global laplacian matrix are optimized separately. The low dimensional representation of training data is obtained by eigen-decomposition of the laplacian matrix. Then the low dimensional representation of testing data is obtained by kernel mapping. Finally, the spherical cover classification model in low dimensional space is constructed. Extensive experiments are conducted on MNIST dataset, YaleB face dataset and AR dataset, and the results verify the effectiveness of the proposed algorithm and its value in the application fields.
