The problem of linking functional connectomics to behavior is extremely challenging due to the complex interactions between the two distinct, but related, data domains. We propose a coupled manifold optimization framework which projects fMRI data onto a low dimensional matrix manifold common to the cohort. The patient specific loadings simultaneously map onto a behavioral measure of interest via a second, non-linear, manifold. By leveraging the kernel trick, we can optimize over a potentially infinite dimensional space without explicitly computing the embeddings. As opposed to conventional manifold learning, which assumes a fixed input representation, our framework directly optimizes for embedding directions that predict behavior. Our optimization algorithm combines proximal gradient descent with the trust region method, which has good convergence guarantees. We validate our framework on resting state fMRI from fifty-eight patients with Autism Spectrum Disorder using three distinct measures of clinical severity. Our method outperforms traditional representation learning techniques in a cross validated setting, thus demonstrating the predictive power of our coupled objective.
Deep sr-DDL: Deep Structurally Regularized Dynamic Dictionary Learning to Integrate Multimodal and Dynamic Functional Connectomics data for Multidimensional Clinical Characterizations
Johns Hopkins University（约翰斯·霍普金斯大学）；Kennedy Krieger Institute（肯尼迪·克里格研究所）；Johns Hopkins School of Medicine（约翰斯·霍普金斯医学院）
From Connectomic to Task-evoked Fingerprints: Individualized Prediction of Task Contrasts from Resting-state Functional Connectivity
Cornell University（康奈尔大学）；Weill Cornell Medicine（威尔康奈尔医学院）；Brain and Mind Research Institute, Weill Cornell Medicine（威尔康奈尔医学院脑与心智研究所）；Nancy E. & Peter C. Meinig School of Biomedical Engineering, Cornell University（康奈尔大学南希·E·与彼得·C·梅尼格生物医学工程学院）
Different representation learning objectives recover distinct latent structures from the same psychometric data
Yale University（耶鲁大学）；Yale School of Public Health（耶鲁公共卫生学院）；VA Connecticut Healthcare System（VA康涅狄格医疗系统）；Cooperative Studies Program Coordinating Center（合作研究项目协调中心）；Center for the Advancement of Research & Development in Educational Technology (CARDET)（教育技术研究与发展促进中心（CARDET））
Integrative neurocybernetic modeling in the era of large-scale neuroscience
Champalimaud Centre for the Unknown（Champalimaud 未知中心）；Janelia Research Campus（Janelia 研究campus）；Harvard University（哈佛大学）；Yale University（哥伦比亚大学）；École Polytechnique Fédérale de Lausanne (EPFL)（瑞士联邦理工学院）；RyvivyR Inc（RyvivyR 公司）
Learning Explainable Representations of Malware Behavior
University of Potsdam（波茨坦大学）；Cisco Systems（思科系统公司）
我们解决了在网络遥测日志中识别恶意软件的问题，并提供了\emph{indicators of compromise} -识别威胁的行为模式的可理解的解释。在我们的系统中，一个专门的检测器阵列抽象的网络流数据到可理解的\emph{network events}在第一步。我们开发了一个神经网络来处理这一系列事件，并识别特定的威胁，恶意软件家族和恶意软件的广泛类别。然后，我们使用\emph{integrated-gradients}方法来突出显示共同构成威胁特征行为模式的事件。我们比较了基于CNN、LSTM和Transformers的网络架构，并在大规模遥测数据上实验性地探索了无监督预训练的有效性。我们演示了该系统如何检测njRAT和其他恶意软件的行为模式的基础上。
Learning Explicit Behavioral Models with Adaptive Questions and World-Model Probes
Artificial Intelligence and Machine Learning Lab（人工智能与机器学习实验室）；Technical University of Darmstadt（德累斯顿技术大学）；Hessian Center for Artificial Intelligence (hessian.AI)（黑森人工智能中心）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；Department of Computer Science（计算机科学系）；Centre for Cognitive Science（认知科学中心）
BLEND: Behavior-guided Neural Population Dynamics Modeling via Privileged Knowledge Distillation
The Hong Kong University of Science and Technology（香港科技大学）；Beijing Institute of Collaborative Innovation（北京协同创新研究院）；Peking University（北京大学）；Beihang University（北京航空航天大学）
