subspace projection approaches to classification and visualization of neural network-level encoding patterns子空间投影的分类方法和可视化的神经网络级编码模式.pdf

Subspace Projection Approaches to Classification and Visualization of Neural Network-Level Encoding Patterns 1 1,2 3 1,2 Remus Os¸an *, Liping Zhu , Shy Shoham , Joe Z. Tsien * 1 Center for Systems Neurobiology, Departments of Pharmacology and Biomedical Engineering, Boston University, Boston, Massachusetts, United States of America, 2 Shanghai Institute of Brain Functional Genomics, The Key Laboratories of Ministry of Education (MOE) and State Science and Technology Committee (SSTC), and Department of Statistical Mathematics, East China Normal University, Shanghai, China, 3 Department of Biomedical Engineering, Technion-Israel Institute of Technology, Haifa, Israel Recent advances in large-scale ensemble recordings allow monitoring of activity patterns of several hundreds of neurons in freely behaving animals. The emergence of such high-dimensional datasets poses challenges for the identification and analysis of dynamical network patterns. While several types of multivariate statistical methods have been used for integrating responses from multiple neurons, their effectiveness in pattern classification and predictive power has not been compared in a direct and systematic manner. Here we systematically employed a series of projection methods, such as Multiple Discriminant Analysis (MDA), Principal Components Analysis (PCA) and Artificial Neural Networks (ANN), and compared them with non-projection multivariate statistical methods such as Multivariate Gaussian Distributions (MGD). Our analyses of hippocampal data recorded during episodic memory events and cortical data simulated during face perception or arm movements illustrate how low-dimensional en